# R. Salakhutdinov

Author pages are created from data sourced from our academic publisher partnerships and public sources.

- Publications
- Influence

Dropout: a simple way to prevent neural networks from overfitting

- Nitish Srivastava, Geoffrey E. Hinton, A. Krizhevsky, Ilya Sutskever, R. Salakhutdinov
- Computer Science
- J. Mach. Learn. Res.
- 2014

Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making… Expand

Reducing the Dimensionality of Data with Neural Networks

- Geoffrey E. Hinton, R. Salakhutdinov
- Medicine, Computer Science
- Science
- 28 July 2006

High-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct high-dimensional input vectors. Gradient descent can… Expand

Probabilistic Matrix Factorization

- R. Salakhutdinov, A. Mnih
- Computer Science
- NIPS
- 3 December 2007

Many existing approaches to collaborative filtering can neither handle very large datasets nor easily deal with users who have very few ratings. In this paper we present the Probabilistic Matrix… Expand

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

- Kelvin Xu, Jimmy Ba, +5 authors Yoshua Bengio
- Computer Science, Mathematics
- ICML
- 10 February 2015

Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the content of images. We describe how we can train… Expand

Improving neural networks by preventing co-adaptation of feature detectors

- Geoffrey E. Hinton, Nitish Srivastava, A. Krizhevsky, Ilya Sutskever, R. Salakhutdinov
- Computer Science
- ArXiv
- 2 July 2012

When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of the… Expand

XLNet: Generalized Autoregressive Pretraining for Language Understanding

- Z. Yang, Zihang Dai, Yiming Yang, J. Carbonell, R. Salakhutdinov, Quoc V. Le
- Computer Science
- NeurIPS
- 19 June 2019

With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language… Expand

Skip-Thought Vectors

- Ryan Kiros, Y. Zhu, +4 authors S. Fidler
- Computer Science
- NIPS
- 22 June 2015

We describe an approach for unsupervised learning of a generic, distributed sentence encoder. Using the continuity of text from books, we train an encoder-decoder model that tries to reconstruct the… Expand

Bayesian probabilistic matrix factorization using Markov chain Monte Carlo

- R. Salakhutdinov, A. Mnih
- Computer Science
- ICML '08
- 5 July 2008

Low-rank matrix approximation methods provide one of the simplest and most effective approaches to collaborative filtering. Such models are usually fitted to data by finding a MAP estimate of the… Expand

Deep Boltzmann Machines

- R. Salakhutdinov, Geoffrey E. Hinton
- Computer Science
- AISTATS
- 15 April 2009

We present a new learning algorithm for Boltzmann machines that contain many layers of hidden variables. Data-dependent expectations are estimated using a variational approximation that tends to… Expand

Neighbourhood Components Analysis

- J. Goldberger, S. Roweis, Geoffrey E. Hinton, R. Salakhutdinov
- Computer Science
- NIPS
- 1 December 2004

In this paper we propose a novel method for learning a Mahalanobis distance measure to be used in the KNN classification algorithm. The algorithm directly maximizes a stochastic variant of the… Expand