Alex Graves (computer scientist): Difference between revisions
rm vague, unsourced statement |
Duncan.Hull (talk | contribs) references |
||
Line 7: | Line 7: | ||
| birth_date = |
| birth_date = |
||
| birth_place = |
| birth_place = |
||
| thesis_title = Supervised sequence labelling with recurrent neural networks |
|||
| occupation = Computer scientist |
|||
| |
| thesis_year = 2008 |
||
| thesis_url = https://www.worldcat.org/oclc/1184353689 |
|||
| known_for = {{Unbulleted list|[[Connectionist temporal classification]] | [[Neural Turing machine]] | [[Differentiable neural computer]]}} |
| known_for = {{Unbulleted list|[[Connectionist temporal classification]] | [[Neural Turing machine]] | [[Differentiable neural computer]]}} |
||
| fields = [[Artificial Intelligence]]<br>[[Recurrent neural network]]s<br>[[Handwriting recognition]]<br>[[Speech recognition]]<ref name=gs/> |
|||
| education = {{Unbulleted list|[[University of Edinburgh]] ([[Bachelor of Science|BSc]]) | [[IDSIA]] ([[Doctor of Philosophy|PhD]])}} |
| education = {{Unbulleted list|[[University of Edinburgh]] ([[Bachelor of Science|BSc]]) | [[IDSIA]] ([[Doctor of Philosophy|PhD]])}} |
||
| workplaces = [[DeepMind]] |
| workplaces = [[DeepMind]]<br>[[University of Toronto]] |
||
}} |
}} |
||
'''Alex Graves''' is a computer scientist and research scientist at [[DeepMind]].<ref name=gs>{{Google scholar id}}</ref> |
|||
⚫ | |||
==Education== |
|||
⚫ | At [[IDSIA]], Graves trained [[long short-term memory]] neural networks by a novel method called [[connectionist temporal classification]] (CTC).<ref name="graves2006">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.</ref> This method outperformed traditional [[speech recognition]] models in certain applications.<ref name="fernandez2007keyword">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.</ref> In 2009, his CTC-trained LSTM was the first [[recurrent neural network]] to win pattern recognition contests, winning several competitions in connected [[handwriting recognition]].<ref>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</ref><ref>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.</ref> |
||
Graves earned his [[Bachelor of Science]] degree in [[Theoretical Physics]] from the [[University of Edinburgh]]{{when}} and a PhD in [[artificial intelligence]] under [[Jürgen Schmidhuber]] at [[IDSIA]].<ref>{{cite web |title=Alex Graves |url=http://www.cifar.ca/alex-graves |website=Canadian Institute for Advanced Research |archive-url=https://web.archive.org/web/20150501222647/http://www.cifar.ca/alex-graves |archive-date=1 May 2015}}</ref> |
|||
==Career and research== |
|||
⚫ | After his PhD, Graves was [[postdoc]] working with Schmidhuber at the [[Technical University of Munich]] and [[Geoffrey Hinton]]<ref name="MyUser_Blog.mikiobraun.de_May_17_2016c">{{cite web |url=http://blog.mikiobraun.de/2014/01/what-deepmind-google.html |title=Marginally Interesting: What is going on with DeepMind and Google? |newspaper=Blog.mikiobraun.de |date= 28 January 2014|author= |accessdate= May 17, 2016}}</ref> at the [[University of Toronto]]. |
||
⚫ | At [[IDSIA]], Graves trained [[long short-term memory]] neural networks by a novel method called [[connectionist temporal classification]] (CTC).<ref name="graves2006">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.</ref> This method outperformed traditional [[speech recognition]] models in certain applications.<ref name="fernandez2007keyword">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. {{doi|10.1007/978-3-540-74695-9_23}}</ref> In 2009, his CTC-trained [[long short-term memory]] (LSTM) was the first [[recurrent neural network]] (RNN) to win pattern recognition contests, winning several competitions in connected [[handwriting recognition]].<ref>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 {{doi|10.5555/2981780.2981848}}</ref><ref>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. {{doi|10.1109/TPAMI.2008.137}}</ref> |
||
[[Google]] uses CTC-trained LSTM for speech recognition on the [[smartphone]].<ref name="GoogleVoiceTranscription">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</ref><ref name="GoogleVoiceSearch">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</ref> |
[[Google]] uses CTC-trained LSTM for speech recognition on the [[smartphone]].<ref name="GoogleVoiceTranscription">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</ref><ref name="GoogleVoiceSearch">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</ref> |
||
Revision as of 06:57, 3 April 2024
Alex Graves | |
---|---|
Education | |
Known for | |
Scientific career | |
Fields | Artificial Intelligence Recurrent neural networks Handwriting recognition Speech recognition[1] |
Institutions | DeepMind University of Toronto |
Thesis | Supervised sequence labelling with recurrent neural networks (2008) |
Alex Graves is a computer scientist and research scientist at DeepMind.[1]
Education
Graves earned his Bachelor of Science degree in Theoretical Physics from the University of Edinburgh[when?] and a PhD in artificial intelligence under Jürgen Schmidhuber at IDSIA.[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 IDSIA, Graves trained long short-term memory 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 long short-term memory (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.[13]
References
- ^ a b Alex Graves publications indexed by Google Scholar
- ^ "Alex Graves". Canadian Institute for Advanced Research. Archived from the original on 1 May 2015.
- ^ "Marginally Interesting: What is going on with DeepMind and Google?". Blog.mikiobraun.de. 28 January 2014. Retrieved 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. doi:10.1007/978-3-540-74695-9_23
- ^ 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 doi:10.5555/2981780.2981848
- ^ 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. doi:10.1109/TPAMI.2008.137
- ^ 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
- ^ "Google's Secretive DeepMind Startup Unveils a "Neural Turing Machine"". Retrieved 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. 538 (7626): 471–476. Bibcode:2016Natur.538..471G. doi:10.1038/nature20101. ISSN 1476-4687. PMID 27732574. S2CID 205251479.
- ^ "Differentiable neural computers | DeepMind". DeepMind. Retrieved 2016-10-19.
- ^ Alex Graves; Rupesh Kumar Srivastava; Timothy Atkinson; Faustino Gomez (14 August 2023), Bayesian Flow Networks (PDF), arXiv:2308.07037, doi:10.48550/ARXIV.2308.07037, Wikidata Q121625910