R
Ruslan Salakhutdinov
Researcher at Carnegie Mellon University
Publications - 457
Citations - 142495
Ruslan Salakhutdinov is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 107, co-authored 410 publications receiving 115921 citations. Previous affiliations of Ruslan Salakhutdinov include Carnegie Learning & University of Toronto.
Papers
More filters
Worst Cases Policy Gradients
TL;DR: This work proposes an actor-critic framework that models the uncertainty of the future and simultaneously learns a policy based on that uncertainty model, and optimize policies for varying levels of conditional Value-at-Risk.
Posted Content
Learning Nonlinear Dynamic Models
TL;DR: A novel approach for learning nonlinear dynamic models leads to a new set of tools capable of solving problems that are otherwise difficult, and is applied to motion capture and high-dimensional video data, yielding results superior to standard alternatives.
Posted Content
A Comparative Study of Word Embeddings for Reading Comprehension
TL;DR: It is shown that seemingly minor choices made on the use of pre-trained word embeddings, and the representation of out-of-vocabulary tokens at test time, can turn out to have a larger impact than architectural choices on the final performance.
Proceedings Article
Exploiting compositionality to explore a large space of model structures
TL;DR: In this paper, a context-free grammar for matrix decomposition models is proposed to automatically choose the decomposition structure from raw data by evaluating only a small fraction of all models.
Patent
Method and apparatus for face recognition
TL;DR: In this article, a training method of training an illumination compensation model includes extracting, from a training image, an albedo image of a face area, a surface normal image of the face area and an illumination feature, the extracting being based on an illumination model; generating an illumination restoration image based on the albedos image, the surface normal images, and the illumination feature.