Dumitru Erhan

Model-Based Reinforcement Learning for Atari

2019 · arXiv (Cornell University)

Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction -- substantially more, in …

Show and tell: A neural image caption generator

2015

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, we present a generative model based on a deep recurrent …

A Benchmark for Interpretability Methods in Deep Neural Networks

2018 · arXiv (Cornell University)

We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification datasets show that many popular interpretability methods produce estimates of feature …