activity
20122022
most citedDistilling the Knowledge in a Neural Network

14.1k citations · 22.2k across the 18 of their papers we have counts for

collaborators
Showing cs.LGShow all

17 papers · 1 filter

cs.LG20228 cited

Gaussian-Bernoulli RBMs Without Tears

Renjie Liao, Simon Kornblith, Mengye Ren +2

We revisit the challenging problem of training Gaussian-Bernoulli restricted Boltzmann machines (GRBMs), introducing two innovations. We propose a novel Gibbs-Langevin sampling alg…

cs.LG20204 cited

Teaching with Commentaries

Aniruddh Raghu, Maithra Raghu, Simon Kornblith +2

Effective training of deep neural networks can be challenging, and there remain many open questions on how to best learn these models. Recently developed methods to improve neural…

cs.LG2020

Big Self-Supervised Models are Strong Semi-Supervised Learners

Ting Chen, Simon Kornblith, Kevin Swersky +2

One paradigm for learning from few labeled examples while making best use of a large amount of unlabeled data is unsupervised pretraining followed by supervised fine-tuning. Althou…

cs.LG202015 cited

Deflecting Adversarial Attacks

Yao Qin, Nicholas Frosst, Colin Raffel +2

There has been an ongoing cycle where stronger defenses against adversarial attacks are subsequently broken by a more advanced defense-aware attack. We present a new approach towar…

cs.LG2020

A Simple Framework for Contrastive Learning of Visual Representations

Ting Chen, Simon Kornblith, Mohammad Norouzi +1

This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms wit…

cs.LG2020

Subclass Distillation

Rafael Müller, Simon Kornblith, Geoffrey Hinton

After a large "teacher" neural network has been trained on labeled data, the probabilities that the teacher assigns to incorrect classes reveal a lot of information about the way i…