Alex Graves | |
---|---|
Education | |
Occupation | Computer scientist |
Known for | |
Scientific career | |
Institutions | DeepMind |
Alex Graves is a computer scientist. Before working as a research scientist at DeepMind, he earned a BSc in Theoretical Physics from the University of Edinburgh and a PhD in artificial intelligence under Jürgen Schmidhuber at IDSIA.[1] He was also a postdoc under Schmidhuber at the Technical University of Munich and under Geoffrey Hinton[2] at the University of Toronto.
At IDSIA, Graves trained long short-term memory neural networks by a novel method called connectionist temporal classification (CTC).[3] This method outperformed traditional speech recognition models in certain applications.[4] In 2009, his CTC-trained LSTM was the first recurrent neural network to win pattern recognition contests, winning several competitions in connected handwriting recognition.[5][6] This method has become very popular. Google uses CTC-trained LSTM for speech recognition on the smartphone.[7][8]
Graves is also the creator of neural Turing machines[9] and the closely related differentiable neural computer.[10][11]