艾力克斯·格雷夫斯 (計算機科學家)

艾力克斯·格雷夫斯(英語:Alex Graves)是一名計算機科學家。在DeepMind擔任研究科學家之前,他在愛丁堡大學獲得理論物理學學士學位,並在IDSIA英语Dalle Molle Institute for Artificial Intelligence Research于爾根·施密德胡伯指導下獲得了人工智慧博士學位[1]。他還曾在慕尼黑工業大學的施密德胡伯和多倫多大學杰弗里·辛顿手下做過博士後[2]

艾力克斯·格雷夫斯
Alex Graves
母校愛丁堡大學BSc
IDSIA英语Dalle Molle Institute for Artificial Intelligence ResearchPhD
知名于連接主義時間分類英语Connectionist temporal classification
神經圖靈機英语Neural Turing machine
可微分神經計算機英语Differentiable neural computer
科学生涯
研究领域計算機科學
机构DeepMind
博士導師于爾根·施密德胡伯

在IDSIA,格雷夫斯通過一種稱為連接主義時間分類英语Connectionist temporal classification(CTC)的新方法訓練長短期記憶神經網路[3]。這種方法在某些應用中的表現優於傳統的語音識別模型[4]。2009年,他的CTC訓練的LSTM是第一個贏得模式識別比賽的循環神經網路,並贏得連接手寫識別方面的幾個比賽[5][6]。這種方法已經變得非常流行。Google在智慧型手機上使用CTC訓練的LSTM進行語音識別[7][8]

格雷夫斯也是神經圖靈機英语Neural Turing machine[9]和密切相關的可微分神經計算機英语Differentiable neural computer的創造者[10][11]

參考資料 编辑

  1. ^ Alex Graves. Canadian Institute for Advanced Research. (原始内容存档于1 May 2015). 
  2. ^ Marginally Interesting: What is going on with DeepMind and Google?. Blog.mikiobraun.de. 28 January 2014 [May 17, 2016]. (原始内容存档于2016-05-22). 
  3. ^ 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.
  4. ^ 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.
  5. ^ 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
  6. ^ 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.
  7. ^ 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页面存档备份,存于互联网档案馆
  8. ^ 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页面存档备份,存于互联网档案馆
  9. ^ Google's Secretive DeepMind Startup Unveils a "Neural Turing Machine". [May 17, 2016]. (原始内容存档于2016-08-13). 
  10. ^ Graves, Alex; Wayne, Greg; Reynolds, Malcolm; Harley, Tim; Danihelka, Ivo; Grabska-Barwińska, Agnieszka; Colmenarejo, Sergio Gómez; Grefenstette, Edward; Ramalho, Tiago. Hybrid computing using a neural network with dynamic external memory. Nature. 2016-10-12, 538 (7626): 471–476 [2023-02-23]. Bibcode:2016Natur.538..471G. ISSN 1476-4687. PMID 27732574. S2CID 205251479. doi:10.1038/nature20101. (原始内容存档于2022-10-02) (英语). 
  11. ^ Differentiable neural computers | DeepMind. DeepMind. [2016-10-19]. (原始内容存档于2023-07-04).