Andriy Mnih

Andriy Mnih

Research Associate
Gatsby Computational Neuroscience Unit
University College London

email: Can be easily derived from the URL for this page.

About me

I now work as a researcher at a London-based machine learning startup. Until February 2013 I was a postdoctoral researcher at Gatsby, working with Yee Whye Teh. Prior to that I was a PhD student in the Machine Learning Group at the University of Toronto, advised by Geoffrey Hinton.

Research interests

representation learning
statistical language modelling
undirected graphical models
large-scale Bayesian learning methods
collaborative filtering

Publications

Learning word embeddings efficiently with noise-contrastive estimation

Advances in Neural Information Processing Systems 26 (NIPS 2013)

Learning Label Trees for Probabilistic Modelling of Implicit Feedback

Advances in Neural Information Processing Systems 25 (NIPS 2012)

A fast and simple algorithm for training neural probabilistic language models

International Conference on Machine Learning 2012 (ICML 2012)

Taxonomy-Informed Latent Factor Models for Implicit Feedback

JMLR W&CP Volume 18: Proceedings of KDD Cup 2011

Improving a Statistical Language Model Through Non-linear Prediction

Neurocomputing, 72:7-9, 2009

A Scalable Hierarchical Distributed Language Model

Advances in Neural Information Processing Systems 21 (NIPS 2008)

Bayesian Probabilistic Matrix Factorization using Markov Chain Monte Carlo

International Conference on Machine Learning 2008 (ICML 2008)

Improving a Statistical Language Model by Modulating the Effects of Context Words

European Symposium on Artificial Neural Networks 2008 (ESANN 2008)

Probabilistic Matrix Factorization

Advances in Neural Information Processing Systems 20 (NIPS 2007)

Three New Graphical Models for Statistical Language Modelling

International Conference on Machine Learning 2007 (ICML 2007)

Restricted Boltzmann Machines for Collaborative Filtering

International Conference on Machine Learning 2007 (ICML 2007)

Visualizing Similarity Data with a Mixture of Maps

AI and Statistics 2007 (AISTATS 2007)

Learning Nonlinear Constraints with Contrastive Backpropagation

International Joint Conference on Neural Networks 2005 (IJCNN 2005)

Wormholes Improve Contrastive Divergence

Advances in Neural Information Processing Systems 16 (NIPS 2003)