Events Add an event Speakers Talks Collections
 

Speakers

Sort by
Newest
Trending
1-30 of 50
1-30 of 50
Filter
Ajay Jain
EECS PhD at UC Berkeley
algorithm, artificial neural network, autoregressive model, bit, color, communication, convolution, convolutional neural network, data compression, deep learning, holography, information, joint probability distribution, lighting, likelihood function, matrix (mathematics), matrix multiplication, maximum likelihood estimation, neural network, parameter, patch (computing), pixel, python (programming language), raster graphics, time series
Soumyasundar Pal
Ph.D. student at McGill University
artificial neural network, atom, calculator, citation, convolution, data, dimension, experiment, future, graph (discrete mathematics), information, laptop, learning, lighting, likelihood function, machine, machine learning, metal, parameter, parametric model, patient, polynomial, proposition, question, solution
Liang Zhang
Global Sales Strategy & Operations at LinkedIn
before deep learning , artificial intelligence , artificial intelligence tutorial, computer science conference , feed and ads modeling, introduction to multimedia, visio-lingual representations, 3d cnns, accent (sociolinguistics), accuracy and precision, acm 2020 tutorial, acoustic model, action recognition, ads recommendation, advertising, algorithm, angle, apache hadoop, apache spark, api, application software, applications at linkedin, array data structure, array data type, art, artificial intelligence tutorial, artificial neural network, assembly language, association for computing machinery, attention, attention (machine learning), average, baby talk, bag-of-words model, bangalore, beef, before deep learning , bible, bichon frise, cartesian coordinate system, castle, central processing unit, click-through rate, closed captioning, code-division multiple access, codec, coherence (physics), color, common technologies for feed and ads recommendation, compass, computer, computer graphics, computer performance, computer science tutorial, computer science tutorials, computer vision, computer vision 2020, computing, concept, convolution, convolutional neural network, cosine similarity, data, data compression, data conversion, data science tutorial, data type, debugging, deconvolution, deep learning, deep learning and cnns, deep learnning, deep learnning tutorial, definition, depiction, design, desk, diagram, diamond, digital image processing, dimension, dsgmm and deep cluster-and-aggregate method, dynamic programming, education, email spam, energy, engine, enzyme kinetics, equation, essay, euclidean vector, experiment, extract, transform, load, feature (machine learning), feature extraction, feature learning, feed recommendation , file system, film frame, finite set, function (mathematics), gas, gender, gradient, grayscale, hidden markov model, histogram, history, hyperparameter optimization, image embeddings, image representations , image segmentation, image understanding, imagenet, improvements on 3d cnn, improvements on 3d cnns and two-stream, infection, information, information retrieval, input/output, inspection, instagram, intelligence, interface (computing), internet, introduction - feed, ads, search and spam, inverted index, k-means clustering, kdd2020 tutorials, language, language model, learning, lecture-style tutorials, letter case, library (computing), likelihood function, linear combination, linearity, linkedin, literature, loader (computing), logic, long short-term memory, machine, machine learning, map, markov chain, markov model, mathematical optimization, matrix (mathematics), mean, meme, memory, metric learning for images, metric space, microsoft, mixture model, mobile app, monotonic function, motivation, moving average, mp3, multimedia, multimedia infrastructure, multimedia search, multimodality, multivariate random variable, music, nature, navigation, neural network, news, non-local networks and slowfast, nothing, number, object detection, online and offline, optical character recognition, optical flow, optimization for cnns, oracle corporation, parameter, parameter (computer programming), parity bit, phoneme, pixel, plasterwork, podcast, precision and recall, prediction, preprocessor, protein–protein interaction, python (programming language), radio, reason, recommender system, recurrent neural network, research, robust statistics, satya nadella, search algorithm, search engine, search engine indexing, self-supervised learning, self-supervised video embeddings, sense, signal, similarity learning, simulation, sms, social media, social networking service, softmax function, software , source lines of code, space, spam detection, spamming, spectral density, spectrogram, speech, speech recognition, speech technologies for video understanding, spotify, statistical classification, statistics, streaming media, string (computer science), subroutine, summation, supervised learning, support-vector machine, temporal topic localization, tensor, texas, three-dimensional space, training, validation, and test sets, transcription (linguistics), transformer (machine learning model), transmission (mechanics), truck, two-stream networks, typing, understanding, unsupervised learning, upload, use case, variance, vector graphics, vector space, video, video captioning, video classification, video embeddings and networks, video game, video game console, video game live streaming, video representations used in production, video search, video search engine, video understanding, weight, youtube
Di Wen
Staff Software Engineer at LinkedIn
before deep learning , artificial intelligence , artificial intelligence tutorial, computer science conference , feed and ads modeling, introduction to multimedia, visio-lingual representations, 3d cnns, accent (sociolinguistics), accuracy and precision, acm 2020 tutorial, acoustic model, action recognition, ads recommendation, advertising, algorithm, angle, apache hadoop, api, application software, applications at linkedin, art, artificial intelligence tutorial, artificial neural network, association for computing machinery, attention, attention (machine learning), average, baby talk, bag-of-words model, bangalore, beef, before deep learning , bible, bichon frise, cartesian coordinate system, castle, central processing unit, click-through rate, closed captioning, code-division multiple access, codec, coherence (physics), common technologies for feed and ads recommendation, compass, computer, computer graphics, computer performance, computer science tutorial, computer science tutorials, computer vision, computer vision 2020, computing, concept, convolution, convolutional neural network, cosine similarity, data, data compression, data science tutorial, deconvolution, deep learning, deep learning and cnns, deep learnning, deep learnning tutorial, definition, depiction, design, desk, diagram, diamond, digital image processing, dimension, dsgmm and deep cluster-and-aggregate method, dynamic programming, education, email spam, energy, engine, enzyme kinetics, equation, essay, euclidean vector, experiment, extract, transform, load, feature (machine learning), feature extraction, feature learning, feed recommendation , film frame, finite set, function (mathematics), gas, gender, gradient, grayscale, hidden markov model, histogram, history, hyperparameter optimization, image embeddings, image representations , image segmentation, image understanding, imagenet, improvements on 3d cnn, improvements on 3d cnns and two-stream, infection, information, information retrieval, input/output, inspection, instagram, intelligence, interface (computing), internet, introduction - feed, ads, search and spam, inverted index, k-means clustering, kdd2020 tutorials, language, language model, learning, lecture-style tutorials, letter case, likelihood function, linear combination, linearity, linkedin, literature, logic, long short-term memory, machine, machine learning, map, markov chain, markov model, mathematical optimization, matrix (mathematics), mean, meme, memory, metric learning for images, metric space, microsoft, mixture model, mobile app, monotonic function, motivation, moving average, mp3, multimedia, multimedia infrastructure, multimedia search, multimodality, multivariate random variable, music, nature, navigation, neural network, news, non-local networks and slowfast, nothing, number, object detection, online and offline, optical character recognition, optical flow, optimization for cnns, oracle corporation, parameter, parity bit, phoneme, pixel, plasterwork, podcast, precision and recall, prediction, protein–protein interaction, radio, reason, recommender system, recurrent neural network, research, robust statistics, satya nadella, search algorithm, search engine, search engine indexing, self-supervised learning, self-supervised video embeddings, sense, signal, similarity learning, simulation, sms, social media, social networking service, softmax function, software , space, spam detection, spamming, spectral density, spectrogram, speech, speech recognition, speech technologies for video understanding, spotify, statistical classification, statistics, streaming media, summation, supervised learning, support-vector machine, temporal topic localization, texas, three-dimensional space, transcription (linguistics), transmission (mechanics), truck, two-stream networks, typing, understanding, unsupervised learning, upload, use case, variance, vector graphics, vector space, video, video captioning, video classification, video embeddings and networks, video game, video game console, video game live streaming, video representations used in production, video search, video search engine, video understanding, weight, youtube
Yijie Dylan Wang
Software Engineering Manager at LinkedIn
before deep learning , artificial intelligence , artificial intelligence tutorial, computer science conference , feed and ads modeling, introduction to multimedia, visio-lingual representations, 3d cnns, accent (sociolinguistics), accuracy and precision, acm 2020 tutorial, acoustic model, action recognition, advertising, algorithm, angle, apache hadoop, api, application software, applications at linkedin, art, artificial intelligence tutorial, artificial neural network, association for computing machinery, attention, attention (machine learning), average, baby talk, bag-of-words model, bangalore, beef, before deep learning , bible, bichon frise, cartesian coordinate system, castle, central processing unit, closed captioning, code-division multiple access, codec, coherence (physics), compass, computer, computer graphics, computer performance, computer science tutorial, computer science tutorials, computer vision, computer vision 2020, computing, concept, convolution, convolutional neural network, data, data compression, data science tutorial, deconvolution, deep learning, deep learning and cnns, deep learnning, deep learnning tutorial, definition, depiction, design, desk, diagram, diamond, digital image processing, dimension, dsgmm and deep cluster-and-aggregate method, dynamic programming, education, email spam, energy, engine, enzyme kinetics, equation, essay, euclidean vector, experiment, extract, transform, load, feature (machine learning), feature extraction, feature learning, film frame, function (mathematics), gas, gender, gradient, grayscale, hidden markov model, histogram, history, hyperparameter optimization, image embeddings, image representations , image segmentation, imagenet, improvements on 3d cnn, improvements on 3d cnns and two-stream, infection, information, information retrieval, input/output, inspection, instagram, intelligence, interface (computing), internet, inverted index, k-means clustering, kdd2020 tutorials, language, language model, learning, lecture-style tutorials, likelihood function, linearity, linkedin, literature, long short-term memory, machine, machine learning, map, markov chain, markov model, mathematical optimization, matrix (mathematics), mean, meme, memory, metric learning for images, metric space, microsoft, mixture model, mobile app, monotonic function, motivation, moving average, mp3, multimedia, multimedia infrastructure, multimodality, music, nature, navigation, neural network, news, non-local networks and slowfast, nothing, number, object detection, online and offline, optical character recognition, optical flow, optimization for cnns, oracle corporation, parameter, parity bit, phoneme, pixel, plasterwork, podcast, precision and recall, prediction, protein–protein interaction, radio, reason, recommender system, recurrent neural network, research, robust statistics, satya nadella, search algorithm, search engine, search engine indexing, self-supervised learning, self-supervised video embeddings, sense, signal, similarity learning, sms, social networking service, softmax function, space, spam detection, spamming, spectral density, spectrogram, speech, speech recognition, speech technologies for video understanding, spotify, statistical classification, statistics, streaming media, supervised learning, support-vector machine, temporal topic localization, texas, three-dimensional space, transcription (linguistics), transmission (mechanics), truck, two-stream networks, typing, understanding, unsupervised learning, upload, use case, variance, vector graphics, vector space, video, video captioning, video classification, video embeddings and networks, video game, video game console, video game live streaming, video search, video search engine, video understanding, weight, youtube
Bharat Jain
Data Scientist at LinkedIn
before deep learning , artificial intelligence , artificial intelligence tutorial, computer science conference , feed and ads modeling, introduction to multimedia, visio-lingual representations, 3d cnns, accent (sociolinguistics), accuracy and precision, acm 2020 tutorial, acoustic model, action recognition, ads recommendation, advertising, algorithm, angle, apache hadoop, api, application software, applications at linkedin, art, artificial intelligence tutorial, artificial neural network, association for computing machinery, attention, attention (machine learning), average, baby talk, bag-of-words model, bangalore, beef, before deep learning , bible, bichon frise, cartesian coordinate system, castle, central processing unit, click-through rate, closed captioning, code-division multiple access, codec, coherence (physics), common technologies for feed and ads recommendation, compass, computer, computer graphics, computer performance, computer science tutorial, computer science tutorials, computer vision, computer vision 2020, computing, concept, convolution, convolutional neural network, cosine similarity, data, data compression, data science tutorial, deconvolution, deep learning, deep learning and cnns, deep learnning, deep learnning tutorial, definition, depiction, design, desk, diagram, diamond, digital image processing, dimension, dsgmm and deep cluster-and-aggregate method, dynamic programming, education, email spam, energy, engine, enzyme kinetics, equation, essay, euclidean vector, experiment, extract, transform, load, feature (machine learning), feature extraction, feature learning, feed recommendation , film frame, finite set, function (mathematics), gas, gender, gradient, grayscale, hidden markov model, histogram, history, hyperparameter optimization, image embeddings, image representations , image segmentation, image understanding, imagenet, improvements on 3d cnn, improvements on 3d cnns and two-stream, infection, information, information retrieval, input/output, inspection, instagram, intelligence, interface (computing), internet, introduction - feed, ads, search and spam, inverted index, k-means clustering, kdd2020 tutorials, language, language model, learning, lecture-style tutorials, letter case, likelihood function, linear combination, linearity, linkedin, literature, logic, long short-term memory, machine, machine learning, map, markov chain, markov model, mathematical optimization, matrix (mathematics), mean, meme, memory, metric learning for images, metric space, microsoft, mixture model, mobile app, monotonic function, motivation, moving average, mp3, multimedia, multimedia infrastructure, multimedia search, multimodality, multivariate random variable, music, nature, navigation, neural network, news, non-local networks and slowfast, nothing, number, object detection, online and offline, optical character recognition, optical flow, optimization for cnns, oracle corporation, parameter, parity bit, phoneme, pixel, plasterwork, podcast, precision and recall, prediction, protein–protein interaction, radio, reason, recommender system, recurrent neural network, research, robust statistics, satya nadella, search algorithm, search engine, search engine indexing, self-supervised learning, self-supervised video embeddings, sense, signal, similarity learning, simulation, sms, social media, social networking service, softmax function, software , space, spam detection, spamming, spectral density, spectrogram, speech, speech recognition, speech technologies for video understanding, spotify, statistical classification, statistics, streaming media, summation, supervised learning, support-vector machine, temporal topic localization, texas, three-dimensional space, transcription (linguistics), transmission (mechanics), truck, two-stream networks, typing, understanding, unsupervised learning, upload, use case, variance, vector graphics, vector space, video, video captioning, video classification, video embeddings and networks, video game, video game console, video game live streaming, video representations used in production, video search, video search engine, video understanding, weight, youtube
Nikita Gupta
Senior Applied Research Engineer at LinkedIn
before deep learning , artificial intelligence , artificial intelligence tutorial, computer science conference , feed and ads modeling, introduction to multimedia, visio-lingual representations, 3d cnns, accent (sociolinguistics), accuracy and precision, acm 2020 tutorial, acoustic model, action recognition, ads recommendation, advertising, algorithm, angle, apache hadoop, api, application software, applications at linkedin, art, artificial intelligence tutorial, artificial neural network, association for computing machinery, attention, attention (machine learning), average, baby talk, bag-of-words model, bangalore, beef, before deep learning , bible, bichon frise, cartesian coordinate system, castle, central processing unit, click-through rate, closed captioning, code-division multiple access, codec, coherence (physics), common technologies for feed and ads recommendation, compass, computer, computer graphics, computer performance, computer science tutorial, computer science tutorials, computer vision, computer vision 2020, computing, concept, convolution, convolutional neural network, cosine similarity, data, data compression, data science tutorial, deconvolution, deep learning, deep learning and cnns, deep learnning, deep learnning tutorial, definition, depiction, design, desk, diagram, diamond, digital image processing, dimension, dsgmm and deep cluster-and-aggregate method, dynamic programming, education, email spam, energy, engine, enzyme kinetics, equation, essay, euclidean vector, experiment, extract, transform, load, feature (machine learning), feature extraction, feature learning, feed recommendation , film frame, finite set, function (mathematics), gas, gender, gradient, grayscale, hidden markov model, histogram, history, hyperparameter optimization, image embeddings, image representations , image segmentation, image understanding, imagenet, improvements on 3d cnn, improvements on 3d cnns and two-stream, infection, information, information retrieval, input/output, inspection, instagram, intelligence, interface (computing), internet, introduction - feed, ads, search and spam, inverted index, k-means clustering, kdd2020 tutorials, language, language model, learning, lecture-style tutorials, letter case, likelihood function, linear combination, linearity, linkedin, literature, logic, long short-term memory, machine, machine learning, map, markov chain, markov model, mathematical optimization, matrix (mathematics), mean, meme, memory, metric learning for images, metric space, microsoft, mixture model, mobile app, monotonic function, motivation, moving average, mp3, multimedia, multimedia infrastructure, multimedia search, multimodality, multivariate random variable, music, nature, navigation, neural network, news, non-local networks and slowfast, nothing, number, object detection, online and offline, optical character recognition, optical flow, optimization for cnns, oracle corporation, parameter, parity bit, phoneme, pixel, plasterwork, podcast, precision and recall, prediction, protein–protein interaction, radio, reason, recommender system, recurrent neural network, research, robust statistics, satya nadella, search algorithm, search engine, search engine indexing, self-supervised learning, self-supervised video embeddings, sense, signal, similarity learning, simulation, sms, social media, social networking service, softmax function, software , space, spam detection, spamming, spectral density, spectrogram, speech, speech recognition, speech technologies for video understanding, spotify, statistical classification, statistics, streaming media, summation, supervised learning, support-vector machine, temporal topic localization, texas, three-dimensional space, transcription (linguistics), transmission (mechanics), truck, two-stream networks, typing, understanding, unsupervised learning, upload, use case, variance, vector graphics, vector space, video, video captioning, video classification, video embeddings and networks, video game, video game console, video game live streaming, video representations used in production, video search, video search engine, video understanding, weight, youtube
Suhit Sinha
Senior Applied Research Engineer at LinkedIn
before deep learning , artificial intelligence , artificial intelligence tutorial, computer science conference , feed and ads modeling, introduction to multimedia, visio-lingual representations, 3d cnns, accent (sociolinguistics), accuracy and precision, acm 2020 tutorial, acoustic model, action recognition, ads recommendation, advertising, algorithm, angle, apache hadoop, api, application software, applications at linkedin, art, artificial intelligence tutorial, artificial neural network, association for computing machinery, attention, attention (machine learning), average, baby talk, bag-of-words model, bangalore, beef, before deep learning , bible, bichon frise, cartesian coordinate system, castle, central processing unit, click-through rate, closed captioning, code-division multiple access, codec, coherence (physics), common technologies for feed and ads recommendation, compass, computer, computer graphics, computer performance, computer science tutorial, computer science tutorials, computer vision, computer vision 2020, computing, concept, convolution, convolutional neural network, cosine similarity, data, data compression, data science tutorial, deconvolution, deep learning, deep learning and cnns, deep learnning, deep learnning tutorial, definition, depiction, design, desk, diagram, diamond, digital image processing, dimension, dsgmm and deep cluster-and-aggregate method, dynamic programming, education, email spam, energy, engine, enzyme kinetics, equation, essay, euclidean vector, experiment, extract, transform, load, feature (machine learning), feature extraction, feature learning, feed recommendation , film frame, finite set, function (mathematics), gas, gender, gradient, grayscale, hidden markov model, histogram, history, hyperparameter optimization, image embeddings, image representations , image segmentation, image understanding, imagenet, improvements on 3d cnn, improvements on 3d cnns and two-stream, infection, information, information retrieval, input/output, inspection, instagram, intelligence, interface (computing), internet, introduction - feed, ads, search and spam, inverted index, k-means clustering, kdd2020 tutorials, language, language model, learning, lecture-style tutorials, letter case, likelihood function, linear combination, linearity, linkedin, literature, logic, long short-term memory, machine, machine learning, map, markov chain, markov model, mathematical optimization, matrix (mathematics), mean, meme, memory, metric learning for images, metric space, microsoft, mixture model, mobile app, monotonic function, motivation, moving average, mp3, multimedia, multimedia infrastructure, multimedia search, multimodality, multivariate random variable, music, nature, navigation, neural network, news, non-local networks and slowfast, nothing, number, object detection, online and offline, optical character recognition, optical flow, optimization for cnns, oracle corporation, parameter, parity bit, phoneme, pixel, plasterwork, podcast, precision and recall, prediction, protein–protein interaction, radio, reason, recommender system, recurrent neural network, research, robust statistics, satya nadella, search algorithm, search engine, search engine indexing, self-supervised learning, self-supervised video embeddings, sense, signal, similarity learning, simulation, sms, social media, social networking service, softmax function, software , space, spam detection, spamming, spectral density, spectrogram, speech, speech recognition, speech technologies for video understanding, spotify, statistical classification, statistics, streaming media, summation, supervised learning, support-vector machine, temporal topic localization, texas, three-dimensional space, transcription (linguistics), transmission (mechanics), truck, two-stream networks, typing, understanding, unsupervised learning, upload, use case, variance, vector graphics, vector space, video, video captioning, video classification, video embeddings and networks, video game, video game console, video game live streaming, video representations used in production, video search, video search engine, video understanding, weight, youtube
Sumit Srivastava
Staff Applied Research Engineer at LinkedIn
before deep learning , artificial intelligence , artificial intelligence tutorial, computer science conference , feed and ads modeling, introduction to multimedia, visio-lingual representations, 3d cnns, accent (sociolinguistics), accuracy and precision, acm 2020 tutorial, acoustic model, action recognition, ads recommendation, advertising, algorithm, angle, apache hadoop, api, application software, applications at linkedin, art, artificial intelligence tutorial, artificial neural network, association for computing machinery, attention, attention (machine learning), average, baby talk, bag-of-words model, bangalore, beef, before deep learning , bible, bichon frise, cartesian coordinate system, castle, central processing unit, click-through rate, closed captioning, code-division multiple access, codec, coherence (physics), common technologies for feed and ads recommendation, compass, computer, computer graphics, computer performance, computer science tutorial, computer science tutorials, computer vision, computer vision 2020, computing, concept, convolution, convolutional neural network, cosine similarity, data, data compression, data science tutorial, deconvolution, deep learning, deep learning and cnns, deep learnning, deep learnning tutorial, definition, depiction, design, desk, diagram, diamond, digital image processing, dimension, dsgmm and deep cluster-and-aggregate method, dynamic programming, education, email spam, energy, engine, enzyme kinetics, equation, essay, euclidean vector, experiment, extract, transform, load, feature (machine learning), feature extraction, feature learning, feed recommendation , film frame, finite set, function (mathematics), gas, gender, gradient, grayscale, hidden markov model, histogram, history, hyperparameter optimization, image embeddings, image representations , image segmentation, image understanding, imagenet, improvements on 3d cnn, improvements on 3d cnns and two-stream, infection, information, information retrieval, input/output, inspection, instagram, intelligence, interface (computing), internet, introduction - feed, ads, search and spam, inverted index, k-means clustering, kdd2020 tutorials, language, language model, learning, lecture-style tutorials, letter case, likelihood function, linear combination, linearity, linkedin, literature, logic, long short-term memory, machine, machine learning, map, markov chain, markov model, mathematical optimization, matrix (mathematics), mean, meme, memory, metric learning for images, metric space, microsoft, mixture model, mobile app, monotonic function, motivation, moving average, mp3, multimedia, multimedia infrastructure, multimedia search, multimodality, multivariate random variable, music, nature, navigation, neural network, news, non-local networks and slowfast, nothing, number, object detection, online and offline, optical character recognition, optical flow, optimization for cnns, oracle corporation, parameter, parity bit, phoneme, pixel, plasterwork, podcast, precision and recall, prediction, protein–protein interaction, radio, reason, recommender system, recurrent neural network, research, robust statistics, satya nadella, search algorithm, search engine, search engine indexing, self-supervised learning, self-supervised video embeddings, sense, signal, similarity learning, simulation, sms, social media, social networking service, softmax function, software , space, spam detection, spamming, spectral density, spectrogram, speech, speech recognition, speech technologies for video understanding, spotify, statistical classification, statistics, streaming media, summation, supervised learning, support-vector machine, temporal topic localization, texas, three-dimensional space, transcription (linguistics), transmission (mechanics), truck, two-stream networks, typing, understanding, unsupervised learning, upload, use case, variance, vector graphics, vector space, video, video captioning, video classification, video embeddings and networks, video game, video game console, video game live streaming, video representations used in production, video search, video search engine, video understanding, weight, youtube
Sirjan Kafle
Senior Machine Learning Engineer, Multimedia AI at LinkedIn
before deep learning , artificial intelligence , artificial intelligence tutorial, computer science conference , feed and ads modeling, introduction to multimedia, visio-lingual representations, 3d cnns, accent (sociolinguistics), accuracy and precision, acm 2020 tutorial, acoustic model, action recognition, ads recommendation, advertising, algorithm, angle, apache hadoop, api, application software, applications at linkedin, art, artificial intelligence tutorial, artificial neural network, association for computing machinery, attention, attention (machine learning), average, baby talk, bag-of-words model, bangalore, beef, before deep learning , bible, bichon frise, cartesian coordinate system, castle, central processing unit, click-through rate, closed captioning, code-division multiple access, codec, coherence (physics), common technologies for feed and ads recommendation, compass, computer, computer graphics, computer performance, computer science tutorial, computer science tutorials, computer vision, computer vision 2020, computing, concept, convolution, convolutional neural network, cosine similarity, data, data compression, data science tutorial, deconvolution, deep learning, deep learning and cnns, deep learnning, deep learnning tutorial, definition, depiction, design, desk, diagram, diamond, digital image processing, dimension, dsgmm and deep cluster-and-aggregate method, dynamic programming, education, email spam, energy, engine, enzyme kinetics, equation, essay, euclidean vector, experiment, extract, transform, load, feature (machine learning), feature extraction, feature learning, feed recommendation , film frame, finite set, function (mathematics), gas, gender, gradient, grayscale, hidden markov model, histogram, history, hyperparameter optimization, image embeddings, image representations , image segmentation, image understanding, imagenet, improvements on 3d cnn, improvements on 3d cnns and two-stream, infection, information, information retrieval, input/output, inspection, instagram, intelligence, interface (computing), internet, introduction - feed, ads, search and spam, inverted index, k-means clustering, kdd2020 tutorials, language, language model, learning, lecture-style tutorials, letter case, likelihood function, linear combination, linearity, linkedin, literature, logic, long short-term memory, machine, machine learning, map, markov chain, markov model, mathematical optimization, matrix (mathematics), mean, meme, memory, metric learning for images, metric space, microsoft, mixture model, mobile app, monotonic function, motivation, moving average, mp3, multimedia, multimedia infrastructure, multimedia search, multimodality, multivariate random variable, music, nature, navigation, neural network, news, non-local networks and slowfast, nothing, number, object detection, online and offline, optical character recognition, optical flow, optimization for cnns, oracle corporation, parameter, parity bit, phoneme, pixel, plasterwork, podcast, precision and recall, prediction, protein–protein interaction, radio, reason, recommender system, recurrent neural network, research, robust statistics, satya nadella, search algorithm, search engine, search engine indexing, self-supervised learning, self-supervised video embeddings, sense, signal, similarity learning, simulation, sms, social media, social networking service, softmax function, software , space, spam detection, spamming, spectral density, spectrogram, speech, speech recognition, speech technologies for video understanding, spotify, statistical classification, statistics, streaming media, summation, supervised learning, support-vector machine, temporal topic localization, texas, three-dimensional space, transcription (linguistics), transmission (mechanics), truck, two-stream networks, typing, understanding, unsupervised learning, upload, use case, variance, vector graphics, vector space, video, video captioning, video classification, video embeddings and networks, video game, video game console, video game live streaming, video representations used in production, video search, video search engine, video understanding, weight, youtube
Aman Gupta
Senior Machine Learning Scientist at LinkedIn Multimedia AI
before deep learning , artificial intelligence , artificial intelligence tutorial, computer science conference , feed and ads modeling, introduction to multimedia, visio-lingual representations, 3d cnns, accent (sociolinguistics), accuracy and precision, acm 2020 tutorial, acoustic model, action recognition, ads recommendation, advertising, algorithm, angle, apache hadoop, api, application software, applications at linkedin, art, artificial intelligence tutorial, artificial neural network, association for computing machinery, attention, attention (machine learning), average, baby talk, bag-of-words model, bangalore, beef, before deep learning , bible, bichon frise, cartesian coordinate system, castle, central processing unit, click-through rate, closed captioning, code-division multiple access, codec, coherence (physics), common technologies for feed and ads recommendation, compass, computer, computer graphics, computer performance, computer science tutorial, computer science tutorials, computer vision, computer vision 2020, computing, concept, convolution, convolutional neural network, cosine similarity, data, data compression, data science tutorial, deconvolution, deep learning, deep learning and cnns, deep learnning, deep learnning tutorial, definition, depiction, design, desk, diagram, diamond, digital image processing, dimension, dsgmm and deep cluster-and-aggregate method, dynamic programming, education, email spam, energy, engine, enzyme kinetics, equation, essay, euclidean vector, experiment, extract, transform, load, feature (machine learning), feature extraction, feature learning, feed recommendation , film frame, finite set, function (mathematics), gas, gender, gradient, grayscale, hidden markov model, histogram, history, hyperparameter optimization, image embeddings, image representations , image segmentation, image understanding, imagenet, improvements on 3d cnn, improvements on 3d cnns and two-stream, infection, information, information retrieval, input/output, inspection, instagram, intelligence, interface (computing), internet, introduction - feed, ads, search and spam, inverted index, k-means clustering, kdd2020 tutorials, language, language model, learning, lecture-style tutorials, letter case, likelihood function, linear combination, linearity, linkedin, literature, logic, long short-term memory, machine, machine learning, map, markov chain, markov model, mathematical optimization, matrix (mathematics), mean, meme, memory, metric learning for images, metric space, microsoft, mixture model, mobile app, monotonic function, motivation, moving average, mp3, multimedia, multimedia infrastructure, multimedia search, multimodality, multivariate random variable, music, nature, navigation, neural network, news, non-local networks and slowfast, nothing, number, object detection, online and offline, optical character recognition, optical flow, optimization for cnns, oracle corporation, parameter, parity bit, phoneme, pixel, plasterwork, podcast, precision and recall, prediction, protein–protein interaction, radio, reason, recommender system, recurrent neural network, research, robust statistics, satya nadella, search algorithm, search engine, search engine indexing, self-supervised learning, self-supervised video embeddings, sense, signal, similarity learning, simulation, sms, social media, social networking service, softmax function, software , space, spam detection, spamming, spectral density, spectrogram, speech, speech recognition, speech technologies for video understanding, spotify, statistical classification, statistics, streaming media, summation, supervised learning, support-vector machine, temporal topic localization, texas, three-dimensional space, transcription (linguistics), transmission (mechanics), truck, two-stream networks, typing, understanding, unsupervised learning, upload, use case, variance, vector graphics, vector space, video, video captioning, video classification, video embeddings and networks, video game, video game console, video game live streaming, video representations used in production, video search, video search engine, video understanding, weight, youtube
Ananth Sankar
Principal Staff Engineer at LinkedIn
before deep learning , artificial intelligence , artificial intelligence tutorial, computer science conference , feed and ads modeling, introduction to multimedia, visio-lingual representations, 3d cnns, accent (sociolinguistics), accuracy and precision, acm 2020 tutorial, acoustic model, action recognition, ads recommendation, advertising, ai, algorithm, angle, apache hadoop, api, application software, applications at linkedin, art, artificial intelligence tutorial, artificial neural network, association for computing machinery, attention, attention (machine learning), automatic summarization, average, baby talk, backpropagation, bag-of-words model, bangalore, beef, before deep learning , bible, bichon frise, black box, cartesian coordinate system, castle, central processing unit, click-through rate, closed captioning, code-division multiple access, codec, coherence (physics), common technologies for feed and ads recommendation, compass, computer, computer graphics, computer performance, computer science tutorial, computer science tutorials, computer vision, computer vision 2020, computing, concept, convolution, convolutional neural network, cosine similarity, cross entropy, data, data compression, data science, data science tutorial, deconvolution, deep learning, deep learning and cnns, deep learnning, deep learnning tutorial, definition, depiction, design, desk, diagram, diamond, digital image processing, dimension, dsgmm and deep cluster-and-aggregate method, dynamic programming, education, email spam, encoding (memory), energy, engine, english language, enzyme kinetics, equation, essay, euclidean vector, experiment, extract, transform, load, feature (machine learning), feature extraction, feature learning, feed recommendation , feedforward neural network, film frame, finite set, four-dimensional space, function (mathematics), gas, gender, gradient, grayscale, hidden markov model, histogram, history, hyperparameter optimization, image embeddings, image representations , image segmentation, image understanding, imagenet, improvements on 3d cnn, improvements on 3d cnns and two-stream, infection, information, information retrieval, input/output, inspection, instagram, intelligence, interface (computing), internet, introduction - feed, ads, search and spam, inverted index, k-means clustering, kdd2020 tutorials, language, language model, learning, lecture-style tutorials, letter case, likelihood function, linear combination, linearity, linkedin, literature, logic, long short-term memory, machine, machine learning, map, markov chain, markov model, mathematical optimization, matrix (mathematics), mean, meme, memory, metric learning for images, metric space, microsoft, mind, mixture model, mobile app, monotonic function, motivation, moving average, mp3, multimedia, multimedia infrastructure, multimedia search, multimodality, multivariate random variable, music, natural language processing, nature, navigation, neural network, neural networks, news, non-local networks and slowfast, nothing, number, object detection, odsc, odsc india, online and offline, optical character recognition, optical flow, optimization for cnns, oracle corporation, parameter, parity bit, phoneme, pixel, plasterwork, podcast, precision and recall, prediction, protein–protein interaction, radio, reason, recommender system, recurrent neural network, research, robust statistics, satya nadella, search algorithm, search engine, search engine indexing, self-supervised learning, self-supervised video embeddings, semantics, sense, signal, similarity learning, simulation, sms, social media, social networking service, softmax function, software , space, spam detection, spamming, spectral density, spectrogram, speech, speech recognition, speech technologies for video understanding, spotify, statistical classification, statistics, streaming media, summation, supervised learning, support-vector machine, temporal topic localization, texas, three-dimensional space, transcription (linguistics), transmission (mechanics), truck, two-stream networks, typing, understanding, unsupervised learning, upload, use case, vanishing gradient problem, variance, vector graphics, vector space, video, video captioning, video classification, video embeddings and networks, video game, video game console, video game live streaming, video representations used in production, video search, video search engine, video understanding, vocabulary, weight, youtube
Julian Togelius
Associate Professor of Computer Science and Engineering at New York University
adaptation, algorithm, art, artificial intelligence, artificial intelligence in video games, artificial life, artificial neural network, association football, atom, average, batman, beach, behaviorism, bipedalism, bit, card game, cell (biology), cogeneration, color, colorado, communication, constraint (mathematics), control flow, control theory, convolution, creativity, data, door, error, evaluation, evolutionary algorithm, experiment, feedback, fitness function, food, fox, function (mathematics), game of chance, games, generation, genetic algorithm, goal, graph (discrete mathematics), greedy algorithm, hanabi (card game), heuristic, hierarchy, hill climbing, history, human, hypothesis, information, intelligence, intersection (road), java (programming language), just say no, kilogram, kullback–leibler divergence, language, learning, linear programming, liver, machine learning, map, mario, mathematical optimization, mathematics, maze, mobile phone, monte carlo method, monte carlo tree search, mood (psychology), mother, motivation, multiplayer video game, music, neural network, neuron, number, overworld, paper, pathfinding, percentage, pisa, playing card, poet, procedural programming, programming language, pronunciation, protein, psychology, python (programming language), radio, reason, red bull, research, robot, ruby (programming language), sampling (statistics), search algorithm, severe acute respiratory syndrome coronavirus 2, signal, singapore, sink, softmax function, space, speed, super mario, super mario bros., tensor, terrain, tile, time complexity, toddler, training, validation, and test sets, tree traversal, turtle, variable (mathematics), video, video game, wii
Samuel Earle
Lecturer in Feature-Writing at UCL
algorithm, artificial intelligence, batman, beach, bit, colorado, convolution, data, feedback, function (mathematics), game of chance, games, goal, hierarchy, information, intelligence, just say no, kilogram, kullback–leibler divergence, language, learning, liver, machine learning, map, mario, maze, mother, motivation, neural network, overworld, paper, percentage, programming language, pronunciation, psychology, radio, red bull, research, sampling (statistics), severe acute respiratory syndrome coronavirus 2, singapore, sink, softmax function, speed, super mario, super mario bros., tensor, training, validation, and test sets, turtle, video game, wii
Philip Bontrager
AI Research Scientist at TheTake.ai
algorithm, artificial intelligence, batman, beach, bit, colorado, convolution, data, feedback, function (mathematics), game of chance, games, goal, hierarchy, information, intelligence, just say no, kilogram, kullback–leibler divergence, language, learning, liver, machine learning, map, mario, maze, mother, motivation, neural network, overworld, paper, percentage, programming language, pronunciation, psychology, radio, red bull, research, sampling (statistics), severe acute respiratory syndrome coronavirus 2, singapore, sink, softmax function, speed, super mario, super mario bros., tensor, training, validation, and test sets, turtle, video game, wii
Ahmed Khalifa
Digital Experience Manager at CILEX
algorithm, artificial intelligence, batman, beach, bit, colorado, convolution, data, feedback, function (mathematics), game of chance, games, goal, hierarchy, information, intelligence, just say no, kilogram, kullback–leibler divergence, language, learning, liver, machine learning, map, mario, maze, mother, motivation, neural network, overworld, paper, percentage, programming language, pronunciation, psychology, radio, red bull, research, sampling (statistics), severe acute respiratory syndrome coronavirus 2, singapore, sink, softmax function, speed, super mario, super mario bros., tensor, training, validation, and test sets, turtle, video game, wii
Bodo Rosenhahn
Professor Computer Vision / Machine Learning at Leibniz University Hannover
algorithm, artificial intelligence, convolution, feedback, function (mathematics), games, goal, hierarchy, information, intelligence, kullback–leibler divergence, learning, machine learning, mario, neural network, overworld, psychology, research, sampling (statistics), softmax function, super mario, super mario bros., tensor, training, validation, and test sets, video game, wii
Frederik Schubert
PhD student at Leibniz University Hannover
algorithm, artificial intelligence, convolution, feedback, function (mathematics), games, goal, hierarchy, information, intelligence, kullback–leibler divergence, learning, machine learning, mario, neural network, overworld, psychology, research, sampling (statistics), softmax function, super mario, super mario bros., tensor, training, validation, and test sets, video game, wii
Maren Awiszus
PhD student at Leibniz University Hannover
algorithm, artificial intelligence, convolution, feedback, function (mathematics), games, goal, hierarchy, information, intelligence, kullback–leibler divergence, learning, machine learning, mario, neural network, overworld, psychology, research, sampling (statistics), softmax function, super mario, super mario bros., tensor, training, validation, and test sets, video game, wii
William L. Hamilton
Assistant Professor of Computer Science at McGill University
association for computing machinery, computer science event 2020, acm 2020, adjacency matrix, complex number, computer science 2020, convolution, deep learning, deep learning 2020, diagonal matrix, diagonalizable matrix, eigenfunction, eigenvalues and eigenvectors, feature learning, filter (signal processing), fourier transform, graph fourier transform, interactome, inverse function, kdd2020, knowledge graph, laplace operator, laplace transform, laplacian matrix, link prediction, machine learning, machine learning 2020, matrix (mathematics), polynomial, protein–protein interaction, recommender system, wave function, will hamilton
Afshin Niktash
Senior Principal Software Engineer at Maxim Integrated
tinyml2021, tinyml2021 talk , accuracy and precision, central processing unit, clock rate, computer, computer science 2021, computer science conference, computer science event 2021, consumption (economics), control data corporation, convolution, convolutional neural network, electric energy consumption, facebook, image editing, interface (computing), kernel (operating system), low-power electronics, machine learning, machine learning techniques, machine learning technologie, machine learning tools, macintosh, memory, microcontroller, microphone, reason, risk, signal, sleep, spectrogram, tinyml foundation
Jan Jongboom
Developer Evangelist IoT at ARM
machine learning approaches, accelerometer, accuracy and precision, algorithm, alphago, altitude, android (operating system), anomaly detection, artificial intelligence, artificial intelligence 2020, artificial neural network, atmospheric pressure, central processing unit, cloud computing, cluster analysis, computer, computer data storage, computer network, computer science, computer science 2021, computer science event, computer science event 2021, convolution, convolutional neural network, correlation and dependence, data compression, deep learning, deepmind, email, embedded system, encryption, engineering, filter (signal processing), future, graph (abstract data type), hyperparameter (machine learning), information technology conference , innovation, intel, intelligence, internet, iot, k-means clustering, keyboard technology, language, latency (engineering), lawyer, learning, learning rate, lora, lorawan, low-pass filter, machine learning, machine learning 2020, machine learning 2021, machine learning techniques, machine learning technologie, machine learning technologies , machine learning tools, map, microsoft, microsoft windows, network, network optimization , neural network, of, parameter, perception, pipeline (computing), pixel, plug and play, prediction, random-access memory, raster graphics, read-only memory, reason, recurrent neural network, sears, sensor, signal, signal processing, spectral density, switch, talk by peter schulmeyer, tax, technologie, the, thermometer, things, tinyml conference 2020, tinyml foundation, tinyml talks 2021, tinyml2021, tinyml2021 talk, ttn, tuner (radio), walt disney world, water
Meng Li
AI Research Scientist at Facebook Inc.
machine learning approaches, accelerometer, accuracy and precision, algorithm, android (operating system), art, artificial intelligence, artificial neural network, basement, brain, brain implant, central processing unit, computer, computer data storage, computer network, computer science, computer science 2021, computer science event, computer science event 2021, convolution, data compression, deep learning, distillation, email, embedded system, encryption, engineering, facebook, filter (signal processing), graph (abstract data type), information, innovation, integrated circuit, intel, intelligence, keyboard technology, language, law, lawyer, learning, learning rate, library, low-pass filter, machine learning, machine learning 2021, machine learning architectures, machine learning techniques, machine learning technologie, machine learning tools, mass, mass media, memory, meng li, microsoft, microsoft windows, network optimization , neural network, parameter, perception, pipeline (computing), pixel, plug and play, protein, random-access memory, raster graphics, read-only memory, reason, recurrent neural network, refrigerator, sanitation, sears, semiconductor, sensor, signal, signal processing, silicon, snapchat, star, switch, talk by meng li, talk by peter schulmeyer, tax, technology, tinyml foundation, tinyml talks 2021, tinyml2021, tinyml2021 talk, truth, tuner (radio), uncertainty, walt disney world
Harsha Viswanath
Azure Edge Device at Principal AI Technical Leader
machine learning approaches, accelerometer, algorithm, android (operating system), artificial intelligence, artificial neural network, central processing unit, computer, computer data storage, computer network, computer science, computer science 2021, computer science event, computer science event 2021, convolution, data compression, deep learning, email, embedded system, encryption, engineering, filter (signal processing), graph (abstract data type), innovation, intel, intelligence, keyboard technology, language, lawyer, learning, learning rate, low-pass filter, machine learning, machine learning 2021, machine learning techniques, machine learning technologie, machine learning tools, microsoft, microsoft windows, network optimization , neural network, parameter, perception, pipeline (computing), pixel, plug and play, random-access memory, raster graphics, read-only memory, reason, recurrent neural network, sears, sensor, signal, signal processing, switch, talk by peter schulmeyer, tax, tinyml foundation, tinyml talks 2021, tinyml2021, tinyml2021 talk, tuner (radio), walt disney world
Ravishankar Sivalingam
Sr. Staff Engineer/Manager at Qualcomm
machine learning approaches, accelerometer, algorithm, android (operating system), artificial intelligence, artificial neural network, augmented reality, camera, central processing unit, computer, computer data storage, computer hardware, computer monitor, computer network, computer science, computer science 2021, computer science event, computer science event 2021, convolution, data compression, deep learning, email, embedded system, encryption, engineering, exposure (photography), eye, eye tracking, facial recognition system, filter (signal processing), frame rate, graph (abstract data type), high frame rate, image resolution, innovation, intel, intelligence, internet of things, keyboard technology, language, lawyer, learning, learning rate, lens, low-pass filter, low-power electronics, machine learning, machine learning 2021, machine learning techniques, machine learning technologie, machine learning tools, microsoft, microsoft windows, mixed reality, network optimization , neural network, parameter, perception, pipeline (computing), pixel, plug and play, random-access memory, raster graphics, read-only memory, reason, recurrent neural network, sears, sensor, shutter speed, signal, signal processing, switch, talk by peter schulmeyer, tax, tinyml foundation, tinyml talks 2021, tinyml2021, tinyml2021 talk, tuner (radio), use case, video, virtual reality, virtual reality headset, visual perception, walt disney world, youtube
Sean McGregor
Member of Technical Staff at Syntiant
machine learning approaches, accelerometer, algorithm, android (operating system), artificial intelligence, artificial neural network, central processing unit, computer, computer data storage, computer network, computer science, computer science 2021, computer science event, computer science event 2021, convolution, data compression, deep learning, email, embedded system, encryption, engineering, filter (signal processing), graph (abstract data type), innovation, intel, intelligence, keyboard technology, language, lawyer, learning, learning rate, low-pass filter, machine learning, machine learning 2021, machine learning techniques, machine learning technologie, machine learning tools, microsoft, microsoft windows, network optimization , neural network, parameter, perception, pipeline (computing), pixel, plug and play, random-access memory, raster graphics, read-only memory, reason, recurrent neural network, sears, sensor, signal, signal processing, switch, talk by peter schulmeyer, tax, tinyml foundation, tinyml talks 2021, tinyml2021, tinyml2021 talk, tuner (radio), walt disney world
Zhi-Gang Liu
Research Engineer at Arm
artificial intelligence , computer science 2021, machine learning 2021, accuracy and precision, arm architecture, arm cortex-m, artificial neural network, auction, benchmark (computing), central processing unit, computer science, computer science event 2021, convolution, coprime integers, coprocessor, crime, deconvolution, euclidean vector, fraction, machine learning technologie, massachusetts, mathematical optimization, mathematics, matrix (mathematics), memory, prediction, quantization (signal processing), semiconductor, silicon, tinyml talks 2021, tinyml2021, trombone
Andrew Davison
Full Professor at Imperial College London
artificial intelligence, automl, bias, camera, communication, computer science, computer vision, convolution, degrees of freedom (mechanics), differentiable memory, dimension, egocentric, fish, ground truth, iclr 2021, iclr virtual conference , image segmentation, image-to-action learning, implicit stereotype, information, learning, long short-term memory, machine learning, mapping, memory, memory protection, mind, multiple-camera setup, network optimization , neural and evolutianary computing, neural architecture search, neural network architectures, neural networks, pixel, research, robot, short-term memory, sms, spatial awareness, spatial memory, truth, unmanned aerial vehicle
Ronald Clark
Corrosion Deputy Technical Lead at National Nuclear Laboratory
artificial intelligence, automl, bias, camera, communication, computer science, computer vision, convolution, degrees of freedom (mechanics), differentiable memory, dimension, egocentric, fish, ground truth, iclr 2021, iclr virtual conference , image segmentation, image-to-action learning, implicit stereotype, information, learning, long short-term memory, machine learning, mapping, memory, memory protection, mind, multiple-camera setup, network optimization , neural and evolutianary computing, neural architecture search, neural network architectures, neural networks, pixel, research, robot, short-term memory, sms, spatial awareness, spatial memory, truth, unmanned aerial vehicle
Stephen James
Postdoc at University of California Berkeley
artificial intelligence, automl, bias, camera, communication, computer science, computer vision, convolution, degrees of freedom (mechanics), differentiable memory, dimension, egocentric, fish, ground truth, iclr 2021, iclr virtual conference , image segmentation, image-to-action learning, implicit stereotype, information, learning, long short-term memory, machine learning, mapping, memory, memory protection, mind, multiple-camera setup, network optimization , neural and evolutianary computing, neural architecture search, neural network architectures, neural networks, pixel, research, robot, short-term memory, sms, spatial awareness, spatial memory, truth, unmanned aerial vehicle
1 2
1-30 of 50