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
Posted Content
Collaborative Filtering in a Non-Uniform World: Learning with the Weighted Trace Norm
TL;DR: In this article, a weighted version of the trace-norm regularizer is proposed for matrix completion with non-uniform sampling, and the experimental results demonstrate that the weighted trace-normal regularization indeed yields significant gains on the (highly nonuniformly sampled) Netflix dataset.
Proceedings ArticleDOI
Exploiting Image-trained CNN Architectures for Unconstrained Video Classification
TL;DR: In this article, different ways of performing spatial and temporal pooling, feature normalization, choice of CNN layers as well as choice of classifiers are explored for event detection in videos using convolutional neural networks (CNNs) trained for image classification.
Learning Representations for Multimodal Data with Deep Belief Nets
TL;DR: The experimental results on bi-modal data consisting of images and text show that the Multimodal DBN can learn a good generative model of the joint space of image and text inputs that is useful for lling in missing data so it can be used both for image annotation and image retrieval.
Proceedings Article
Path-SGD: path-normalized optimization in deep neural networks
TL;DR: Path-SGD as mentioned in this paper is an approximate steepest descent method with respect to a path-wise regularizer related to max-norm regularization, which is easy and efficient to implement and leads to empirical gains over SGD.
Proceedings ArticleDOI
Robust Boltzmann Machines for recognition and denoising
TL;DR: This paper introduces a novel model, the Robust Boltzmann Machine (RoBM), which allows BoltZmann Machines to be robust to corruptions and is significantly better at recognition and denoising on several face databases.