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
On the Quantitative Analysis of Decoder-Based Generative Models
TL;DR: This work proposes to use Annealed Importance Sampling for evaluating log-likelihoods for decoder-based models and validate its accuracy using bidirectional Monte Carlo, and analyzes the performance of decoded models, the effectiveness of existing log- likelihood estimators, the degree of overfitting, and the degree to which these models miss important modes of the data distribution.
Proceedings ArticleDOI
segDeepM: Exploiting segmentation and context in deep neural networks for object detection
TL;DR: In this paper, the authors propose an approach that exploits object segmentation in order to improve the accuracy of object detection, and frame the problem as inference in a Markov Random Field, in which each detection hypothesis scores object appearance as well as contextual information using Convolutional Neural Networks.
Posted Content
Neural Map: Structured Memory for Deep Reinforcement Learning
TL;DR: This paper develops a memory system with an adaptable write operator that is customized to the sorts of 3D environments that DRL agents typically interact with and demonstrates empirically that the Neural Map surpasses previous DRL memories on a set of challenging 2D and 3D maze environments.
Proceedings ArticleDOI
Transformer Dissection: An Unified Understanding for Transformer's Attention via the Lens of Kernel
TL;DR: A new formulation of attention via the lens of the kernel is presented, which models the input as a product of symmetric kernels and achieves competitive performance to the current state of the art model with less computation.
Proceedings Article
A Better Way to Pretrain Deep Boltzmann Machines
TL;DR: A different method of pretraining DBMs is developed that distributes the modelling work more evenly over the hidden layers and demonstrates that the new pretraining algorithm allows us to learn better generative models.