Alex Graves (computer scientist)

Graves earned his Bachelor of Science degree in Theoretical Physics from the University of Edinburgh{{when|date=April 2024}} 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.{{cite thesis|first=Alex|last=Graves|degree=PhD|oclc=1184353689|title=Supervised sequence labelling with recurrent neural networks |year=2008|url=https://www.cs.toronto.edu/~graves/phd.pdf|publisher=Technischen Universitat Munchen}}{{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}}

After his PhD, Graves was postdoc working with Schmidhuber at the Technical University of Munich and Geoffrey Hinton{{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}} 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).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. This method outperformed traditional speech recognition models in certain applications.{{cite book | doi=10.1007/978-3-540-74695-9_23 | chapter=An Application of Recurrent Neural Networks to Discriminative Keyword Spotting | title=Artificial Neural Networks – ICANN 2007 | series=Lecture Notes in Computer Science | date=2007 | last1=Fernández | first1=Santiago | last2=Graves | first2=Alex | last3=Schmidhuber | first3=Jürgen | volume=4669 | pages=220–229 | isbn=978-3-540-74693-5 }} 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.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 https://dl.acm.org/doi/10.5555/2981780.2981848{{cite journal | doi=10.1109/TPAMI.2008.137 | title=A Novel Connectionist System for Unconstrained Handwriting Recognition | date=2009 | last1=Graves | first1=A. | last2=Liwicki | first2=M. | last3=Fernandez | first3=S. | last4=Bertolami | first4=R. | last5=Bunke | first5=H. | last6=Schmidhuber | first6=J. | journal=IEEE Transactions on Pattern Analysis and Machine Intelligence | volume=31 | issue=5 | pages=855–868 | pmid=19299860 }}

Google uses CTC-trained LSTM for speech recognition on the smartphone.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.htmlGoogle 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

Graves is also the creator of neural Turing machines{{cite web |url=https://www.technologyreview.com/s/532156/googles-secretive-deepmind-startup-unveils-a-neural-turing-machine/ |title=Google's Secretive DeepMind Startup Unveils a "Neural Turing Machine" |newspaper= |date= |author= |accessdate= May 17, 2016}} and the closely related differentiable neural computer.{{Cite journal|last1=Graves|first1=Alex|last2=Wayne|first2=Greg|last3=Reynolds|first3=Malcolm|last4=Harley|first4=Tim|last5=Danihelka|first5=Ivo|last6=Grabska-Barwińska|first6=Agnieszka|last7=Colmenarejo|first7=Sergio Gómez|last8=Grefenstette|first8=Edward|last9=Ramalho|first9=Tiago|date=2016-10-12|title=Hybrid computing using a neural network with dynamic external memory|journal=Nature|language=en|volume=538|issue=7626|doi=10.1038/nature20101|issn=1476-4687|pages=471–476|pmid=27732574|bibcode=2016Natur.538..471G|s2cid=205251479|url=https://ora.ox.ac.uk/objects/uuid:dd8473bd-2d70-424d-881b-86d9c9c66b51}}{{Cite web|url=https://deepmind.com/blog/differentiable-neural-computers/|title=Differentiable neural computers {{!}} DeepMind|website=DeepMind|access-date=2016-10-19}} In 2023, he wrote the paper Bayesian Flow Networks.{{cite arXiv |eprint=2308.07037 |last1=Graves |first1=Alex |author2=Rupesh Kumar Srivastava |last3=Atkinson |first3=Timothy |last4=Gomez |first4=Faustino |title=Bayesian Flow Networks |date=2023 |class=cs.LG }}

{{Reflist}}

{{Authority control}}

{{DEFAULTSORT:Graves, Alex}}

Category:Living people

Category:British artificial intelligence researchers

Category:Scottish computer scientists

Category:Alumni of the University of Edinburgh

Category:Year of birth missing (living people)

Category:Place of birth missing (living people)