Scientific originatorArchitecture researcher
Yoshua Bengio
Built the first neural language model and the attention mechanism for translation that later became the core of the Transformer.
Works in the archive (7) · lead author on 1
- Learning Long-Term Dependencies is Difficult (vanishing gradients) · 1994
- LeNet: Gradient-Based Learning Applied to Document Recognition · 1998
- LeadA Neural Probabilistic Language Model · 2003
- Understanding the Difficulty of Training Deep Nets (Xavier/He init) · 2010
- Rectified Linear Units (ReLU) · 2010
- Neural Machine Translation by Jointly Learning to Align and Translate (Bahdanau attention) · 2014
- Gated Recurrent Unit (GRU) / RNN Encoder-Decoder · 2014
“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.
Co-authors in the archive
View co-author network (20 people)
Loading graph…