I
Ilya Sutskever
Researcher at OpenAI
Publications - 137
Citations - 294374
Ilya Sutskever is an academic researcher from OpenAI. The author has contributed to research in topics: Artificial neural network & Reinforcement learning. The author has an hindex of 75, co-authored 131 publications receiving 235539 citations. Previous affiliations of Ilya Sutskever include Google & University of Toronto.
Papers
More filters
Posted Content
Neural GPUs Learn Algorithms
Łukasz Kaiser,Ilya Sutskever +1 more
TL;DR: The Neural GPU as discussed by the authors is based on a type of convolutional gated recurrent unit and is computationally universal, unlike the NTM, it is highly parallel which makes it easier to train and efficient to run.
Proceedings Article
Learning Multilevel Distributed Representations for High-Dimensional Sequences
TL;DR: A new family of non-linear sequence models that are substantially more powerful than hidden Markov models or linear dynamical systems are described, and their performance is demonstrated using synthetic video sequences of two balls bouncing in a box.
Book ChapterDOI
Training Deep and Recurrent Networks with Hessian-Free Optimization
James Martens,Ilya Sutskever +1 more
TL;DR: This chapter describes the basic HF approach, and examines well-known performance-improving techniques such as preconditioning which have been beneficial for neural network training and others of a more heuristic nature which are harder to justify, but which have found to work well in practice.
Posted Content
Neural Programmer: Inducing Latent Programs with Gradient Descent
TL;DR: Neural Programmer as discussed by the authors is an end-to-end differentiable neural network augmented with a small set of basic arithmetic and logic operations, which can call these augmented operations over several steps, thereby inducing compositional programs that are more complex than the built-in operations.
Posted Content
Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
TL;DR: In this article, a gradient-based meta-learning algorithm is proposed for continuous adaptation in dynamically changing and adversarial scenarios, and the authors design a new multi-agent competitive environment, RoboSumo, and define iterated adaptation games for testing various aspects of continuous adaptation strategies.