Alex Graves (computer scientist) explained
Alex Graves is a computer scientist and research scientist at DeepMind.
Education
Graves earned his Bachelor of Science degree in Theoretical Physics from the University of Edinburgh and a PhD in artificial intelligence from the Technical University of Munich supervised by Jürgen Schmidhuber at the Dalle Molle Institute for Artificial Intelligence Research.[1] [2]
Career and research
After his PhD, Graves was postdoc working with Schmidhuber at the Technical University of Munich and Geoffrey Hinton[3] at the University of Toronto.
At the Dalle Molle Institute for Artificial Intelligence Research, Graves trained long short-term memory (LSTM) neural networks by a novel method called connectionist temporal classification (CTC).[4] This method outperformed traditional speech recognition models in certain applications.[5] In 2009, his CTC-trained LSTM was the first recurrent neural network (RNN) to win pattern recognition contests, winning several competitions in connected handwriting recognition.[6] [7] Google uses CTC-trained LSTM for speech recognition on the smartphone.[8] [9]
Graves is also the creator of neural Turing machines[10] and the closely related differentiable neural computer.[11] [12] In 2023, he published the paper Bayesian Flow Networks.
Notes and References
- Alex. Graves. PhD. 1184353689. Supervised sequence labelling with recurrent neural networks . 2008. Technischen Universitat Munchen.
- Web site: Alex Graves . Canadian Institute for Advanced Research . https://web.archive.org/web/20150501222647/http://www.cifar.ca/alex-graves . 1 May 2015.
- Web site: Marginally Interesting: What is going on with DeepMind and Google? . Blog.mikiobraun.de . 28 January 2014. May 17, 2016.
- Alex Graves, Santiago Fernandez, Faustino Gomez, and Jürgen Schmidhuber (2006). Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural nets. Proceedings of ICML’06, pp. 369–376.
- Santiago Fernandez, Alex Graves, and Jürgen Schmidhuber (2007). An application of recurrent neural networks to discriminative keyword spotting. Proceedings of ICANN (2), pp. 220–229.
- Graves, Alex; and Schmidhuber, Jürgen; Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks, in Bengio, Yoshua; Schuurmans, Dale; Lafferty, John; Williams, Chris K. I.; and Culotta, Aron (eds.), Advances in Neural Information Processing Systems 22 (NIPS'22), December 7th–10th, 2009, Vancouver, BC, Neural Information Processing Systems (NIPS) Foundation, 2009, pp. 545–552
- A. Graves, M. Liwicki, S. Fernandez, R. Bertolami, H. Bunke, J. Schmidhuber. A Novel Connectionist System for Improved Unconstrained Handwriting Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 5, 2009.
- Google Research Blog. The neural networks behind Google Voice transcription. August 11, 2015. By Françoise Beaufays http://googleresearch.blogspot.co.at/2015/08/the-neural-networks-behind-google-voice.html
- Google Research Blog. Google voice search: faster and more accurate. September 24, 2015. By Haşim Sak, Andrew Senior, Kanishka Rao, Françoise Beaufays and Johan Schalkwyk – Google Speech Team http://googleresearch.blogspot.co.uk/2015/09/google-voice-search-faster-and-more.html
- Web site: Google's Secretive DeepMind Startup Unveils a "Neural Turing Machine" . May 17, 2016.
- Graves. Alex. Wayne. Greg. Reynolds. Malcolm. Harley. Tim. Danihelka. Ivo. Grabska-Barwińska. Agnieszka. Colmenarejo. Sergio Gómez. Grefenstette. Edward. Ramalho. Tiago. 2016-10-12. Hybrid computing using a neural network with dynamic external memory. Nature. en. 538. 7626. 10.1038/nature20101. 1476-4687. 471–476. 27732574. 2016Natur.538..471G. 205251479.
- Web site: Differentiable neural computers DeepMind. DeepMind. 2016-10-19.
