most citedUnderstanding deep learning requires rethinking generalization

1.1k citations · 2.9k across the 7 of their papers we have counts for

collaborators
Showing 2016Show all

6 papers · 1 filter

cs.AI2016278 cited

Neural Combinatorial Optimization with Reinforcement Learning

Irwan Bello, Hieu Pham, Quoc V. Le +2

This paper presents a framework to tackle combinatorial optimization problems using neural networks and reinforcement learning. We focus on the traveling salesman problem (TSP) and…

cs.LG20161.1k cited

Understanding deep learning requires rethinking generalization

Chiyuan Zhang, Samy Bengio, Moritz Hardt +2

Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance. Conventional wisdom attribut…

cs.CV2016375 cited

Adversarial Machine Learning at Scale

Alexey Kurakin, Ian Goodfellow, Samy Bengio

Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks wit…

cs.LG201616 cited

Can Active Memory Replace Attention?

Łukasz Kaiser, Samy Bengio

Several mechanisms to focus attention of a neural network on selected parts of its input or memory have been used successfully in deep learning models in recent years. Attention ha…

cs.CV2016922 cited

Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge

Oriol Vinyals, Alexander Toshev, Samy Bengio +1

Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, w…

cs.LG201688 cited

Reward Augmented Maximum Likelihood for Neural Structured Prediction

Mohammad Norouzi, Samy Bengio, Zhifeng Chen +4

A key problem in structured output prediction is direct optimization of the task reward function that matters for test evaluation. This paper presents a simple and computationally…