Yoshua Bengio

Professor 路 Kumamoto University

Nanyang Technological University

Advertisement

Support free Japanese study resources

Advertisement area

h-index183
Publications1,278
Last 5y386
English accessEnglish-language information not found on lab site

Research summary

A comparison of multilayer neural networks trained by back-propagation on handwritten character recognition showed that convolutional neural networks, designed to handle the variability of 2D shapes, outperform other techniques on a standard handwritten digit task and can synthesise complex decision surfaces directly from high-dimensional patterns with minimal preprocessing [1]. An analysis of gradient-based training of recurrent neural networks demonstrated that capturing long-term temporal dependencies becomes increasingly difficult as the duration of those dependencies grows, exposing a trade-off between efficient gradient-based learning and reliable latching of information over long intervals, and motivating alternatives to standard gradient descent [7]. A study of standard gradient descent applied to deep feed-forward networks from random initialization examined the role of non-linear activation functions and the propagation of activations and gradients across layers, clarifying why such training had failed before 2006 and informing subsequent initialization schemes [5]. An RNN encoder-decoder architecture was introduced for statistical machine translation, learning phrase representations that improve translation quality [2]. An empirical evaluation of gated recurrent units, including LSTM and the newer gated recurrent unit (GRU), on polyphonic music modelling and speech-signal modelling found that gated units outperform tanh units and that GRUs are broadly comparable to LSTMs [6]. A review of representation learning argued that the difficulty of machine-learning tasks reflects how well a representation disentangles the explanatory factors behind the data, and surveyed probabilistic models, autoencoders, manifold learning and deep networks under generic priors [4]. A textbook-style treatment of deep learning frames the field as a hierarchical learning paradigm in which simpler concepts compose into more complex ones, covering background in linear algebra, probability and information theory alongside model families [8]. Generative adversarial networks (GANs) are described as deep generative models that learn distributions implicitly and produce realistic high-resolution images [3]. Graph attention networks (GATs) use masked self-attention to assign different weights to neighbours in graph-structured data without costly matrix operations [9].

Recent publications

  1. Deep learning2015 路 Nature 路 80284 citationsDOI
  2. Gradient-based learning applied to document recognition1998 路 Proceedings of the IEEE 路 57592 citationsDOI
  3. Learning Phrase Representations using RNN Encoder鈥揇ecoder for Statistical Machine Translation2014 路 24160 citationsDOI
  4. Generative adversarial networks2020 路 Communications of the ACM 路 13316 citationsDOI
  5. Representation Learning: A Review and New Perspectives2013 路 IEEE Transactions on Pattern Analysis and Machine Intelligence 路 12849 citationsDOI
  6. Understanding the difficulty of training deep feedforward neural networks2010 路 12676 citations
  7. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling2014 路 arXiv (Cornell University) 路 10772 citationsDOI
  8. Deep Learning2016 路 MIT Press eBooks 路 8959 citations
  9. Learning long-term dependencies with gradient descent is difficult1994 路 IEEE Transactions on Neural Networks 路 8376 citationsDOI
  10. Graph Attention Networks2017 路 arXiv (Cornell University) 路 8306 citations

The lab page does not clearly state student acceptance status. Email the professor directly to confirm.

How to apply

Email Yoshua Bengio 6-12 months before your application deadline. Read several recent papers and reference specific work in your message. Use our how to email a Japanese professor guide for the proven email structure.

For applications via MEXT scholarship: see our MEXT 2027 complete guide and university-specific University Recommendation track.

External profiles

Profile compiled from public sources (Researchmap, OpenAlex, Kumamoto University faculty directory). Last refreshed 2026-05. Report incorrect information.

Advertisement

Support free Japanese study resources

Advertisement area