I
Ian Goodfellow
Researcher at Google
Publications - 139
Citations - 178656
Ian Goodfellow is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & MNIST database. The author has an hindex of 85, co-authored 137 publications receiving 135390 citations. Previous affiliations of Ian Goodfellow include OpenAI & Université de Montréal.
Papers
More filters
Posted Content
Adversarial Machine Learning at Scale
TL;DR: This paper showed that adversarial training confers robustness to single-step attack methods, while multi-step attacks are somewhat less transferable than single step attack methods and single step attacks are the best for mounting black-box attacks.
Proceedings Article
Self-Attention Generative Adversarial Networks
TL;DR: The proposed SAGAN achieves the state-of-the-art results, boosting the best published Inception score from 36.8 to 52.52 and reducing Frechet Inception distance from 27.62 to 18.65 on the challenging ImageNet dataset.
Posted Content
Sanity Checks for Saliency Maps
TL;DR: It is shown that some existing saliency methods are independent both of the model and of the data generating process, and methods that fail the proposed tests are inadequate for tasks that are sensitive to either data or model.
Posted Content
Practical Black-Box Attacks against Machine Learning
TL;DR: In this article, a black-box attack strategy consists in training a local model to substitute for the target DNN, using inputs synthetically generated by an adversary and labeled by the targeted DNN.
Posted Content
An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
TL;DR: In this article, the authors investigate the extent to which the catastrophic forgetting problem occurs for modern neural networks, comparing both established and recent gradient-based training algorithms and activation functions and find that the dropout algorithm is consistently best at adapting to the new task, remembering the old task and has the best tradeoff curve between these two extremes.