Tomas Mikolov

Facebook AI Research

I am a research scientist at Facebook AI Research since May 2014. Previously I have been member of Google Brain team, where I developed and implemented efficient algorithms for computing distributed representations of words (word2vec project). I have obtained my PhD from Brno University of Technology (Czech Republic) for my work on recurrent neural network based language models (RNNLM). My long term research goal is to develop intelligent machines capable of learning and communication with people using natural language.

Interests

Machine learning, and natural language processing

Google Scholar Profile

Interests

Latest Publications

Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion

Advances in Pre-Training Distributed Word Representations

Efficient Large-Scale Multi-Modal Classification

Enriching Word Vectors with Subword Information

CommAI: Evaluating the First Steps Towards a Useful General AI

Variable Computation in Recurrent Neural Networks

Bag of Tricks for Efficient Text Classification

A Roadmap Towards Machine Intelligence

Learning Simple Algorithms from Examples

Alternative Structures for Character-Level RNNs

Learning Longer Memory in Recurrent Neural Networks

Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets

Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews

Show More Publications

News

Expanded fastText library

fastText

Facebook Researchers Focus on the Most Challenging Machine Learning Questions at ICML 2016

Inferring Algorithmic Patterns with Stack

Using Neural Networks for Modeling and Representing Natural Languages

Show More News