Representation Learning for Reading Comprehension

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=ZSDrM-tuOiA


Duration: 45:01
1,800 views
22

Russ Salakhutdinov, Carnegie Mellon University
Representation Learning
https://simons.berkeley.edu/talks/russ-salakhutdinov-2017-3-29



Other Videos By Simons Institute for the Theory of Computing


2017-03-31Formation and Association of Symbolic Memories in the Brain
2017-03-31Learning Paraphrastic Representations of Natural Language Sentences
2017-03-30Provably Learning of Noisy-or Networks
2017-03-30Unsupervised Representation Learning
2017-03-30Generalization and Equilibrium in Generative Adversarial Nets (GANs)
2017-03-30Representation Learning of Grounded Language and Knowledge: with and without End-to-End Learning
2017-03-30Re-Thinking Representational Learning in Robotics and Music
2017-03-29Spotlight Talk: How to Escape Saddle Points Efficiently
2017-03-29Tractable Learning in Structured Probability Spaces
2017-03-29Spotlight Talk: Convolutional Dictionary Learning through Tensor Factorization
2017-03-29Representation Learning for Reading Comprehension
2017-03-29Evaluating Neural Network Representations Against Human Cognition
2017-03-29Adversarial Perceptual Representation Learning Across Diverse Modalities and Domains
2017-03-29Continuous State Machines and Grammars for Linguistic Structure Prediction
2017-03-28Failures of Deep Learning
2017-03-28Supersizing Self-Supervision: Learning Perception and Action without Human Supervision
2017-03-28Deep Reinforcement Learning
2017-03-28Learning from Unlabeled Video
2017-03-28Unsupervised Discovery Through Adversarial Self-Play
2017-03-27Spotlight Talk: Semi-Random Units for Learning Neural Networks with Guarantees
2017-03-27Spotlight Talk: A Formalization of Representation Learning


Tags:
Simons Institute
Theory of Computing
Theory of Computation
Theoretical Computer Science
Computer Science
UC Berkeley
Russ Salakhutdinov
Representation Learning