Published Dec 6, 2020

#032- Simon Kornblith / GoogleAI - SimCLR and Paper Haul!

Explore the transformative impact of loss functions, neural network representations, and contrastive learning techniques with Google Brain's Simon Kornblith as he delves into the SimCLR framework, revealing groundbreaking insights in self-supervised learning and transfer learning efficiency.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

Explainability, Reasoning, Priors and GPT-3
Answers 383 questions
Kernels!
Answers 383 questions
Understanding Deep Learning - Prof. SIMON PRINCE [STAFF FAVOURITE]
Answers 383 questions
ICLR 2020: Yoshua Bengio and the Nature of Consciousness
Answers 383 questions
#041 - Biologically Plausible Neural Networks - Dr. Simon Stringer
Answers 383 questions
Jürgen Schmidhuber - Neural and Non-Neural AI, Reasoning, Transformers, and LSTMs
Answers 383 questions
Computation, Bayesian Model Selection, Interactive Articles
Answers 383 questions
MLST #78 - Prof. NOAM CHOMSKY (Special Edition)
Answers 383 questions
#035 Christmas Community Edition!
Answers 383 questions
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
Answers 383 questions
#045 Microsoft's Platform for Reinforcement Learning (Bonsai)
Answers 383 questions
#046 The Great ML Stagnation (Mark Saroufim and Dr. Mathew Salvaris)
Answers 383 questions
#54 Gary Marcus and Luis Lamb - Neurosymbolic models
Answers 383 questions
#55 Self-Supervised Vision Models (Dr. Ishan Misra - FAIR).
Answers 383 questions
#57 - Prof. Melanie Mitchell - Why AI is harder than we think
Answers 383 questions

Dexa/Machine Learning Street Talk (MLST)

#032- Simon Kornblith / GoogleAI - SimCLR and Paper Haul!

Topics covered

Popular Clips

Image Representation Learning

Self-Supervised Learning

Contrastive Learning Insights

Neural Network Expressibility

Machine Learning Insights

Neural Network Representations

Learning Representations Dynamically

Julia's Advantages

Evolution of Data Augmentation

Evolution of Neural Networks

Neural Network Similarity

Loss Function Impact

Self-Supervised Learning Insights

Evolution of Representations

Data Augmentation Insights

Episode Highlights

Impact of Loss Functions

Neural Network Representations

Contrastive Learning Techniques

Related Episodes

Explainability, Reasoning, Priors and GPT-3

Kernels!

Understanding Deep Learning - Prof. SIMON PRINCE [STAFF FAVOURITE]

ICLR 2020: Yoshua Bengio and the Nature of Consciousness

#041 - Biologically Plausible Neural Networks - Dr. Simon Stringer

Jürgen Schmidhuber - Neural and Non-Neural AI, Reasoning, Transformers, and LSTMs

Computation, Bayesian Model Selection, Interactive Articles

MLST #78 - Prof. NOAM CHOMSKY (Special Edition)

#035 Christmas Community Edition!

CURL: Contrastive Unsupervised Representations for Reinforcement Learning

#045 Microsoft's Platform for Reinforcement Learning (Bonsai)

#046 The Great ML Stagnation (Mark Saroufim and Dr. Mathew Salvaris)

#54 Gary Marcus and Luis Lamb - Neurosymbolic models

#55 Self-Supervised Vision Models (Dr. Ishan Misra - FAIR).

#57 - Prof. Melanie Mitchell - Why AI is harder than we think

#032- Simon Kornblith / GoogleAI - SimCLR and Paper Haul!

Topics covered

Popular Clips

Episode Highlights

Impact of Loss Functions

Neural Network RepresentationsSimon Kornblith from Google Brain explores the intricacies of neural network representations and their evolution. He introduces innovative methods to measure similarity and discusses the implications of network architecture on learning efficiency.

Neural Network Representations

Contrastive Learning Techniques

Related Episodes