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
Journal ArticleDOI
Semantic hashing
TL;DR: In this paper, a deep graphical model of the word-count vectors obtained from a large set of documents is proposed. But the model is restricted to the deep layer of the deep neural network and cannot handle large numbers of documents.
Posted Content
Skip-Thought Vectors
Ryan Kiros,Yukun Zhu,Ruslan Salakhutdinov,Richard S. Zemel,Antonio Torralba,Raquel Urtasun,Sanja Fidler +6 more
TL;DR: The approach for unsupervised learning of a generic, distributed sentence encoder is described, using the continuity of text from books to train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded passage.
Proceedings Article
Revisiting semi-supervised learning with graph embeddings
TL;DR: In this article, a semi-supervised learning framework based on graph embeddings is proposed, where given a graph between instances, an embedding for each instance is trained to jointly predict the class label and the neighborhood context in the graph.
Proceedings Article
Multimodal Learning with Deep Boltzmann Machines
TL;DR: In this paper, a Deep Boltzmann Machine (DBM) is proposed for learning a generative model of data that consists of multiple and diverse input modalities, which can be used to extract a unified representation that fuses modalities together.
Proceedings ArticleDOI
Evaluation methods for topic models
TL;DR: It is demonstrated experimentally that commonly-used methods are unlikely to accurately estimate the probability of held-out documents, and two alternative methods that are both accurate and efficient are proposed.