艾力克斯·格雷夫斯(英语:Alex Graves)是一名计算机科学家。在DeepMind担任研究科学家之前,他在爱丁堡大学获得理论物理学学士学位,并在IDSIA的于尔根·施密德胡伯指导下获得了人工智能博士学位[1]。他还曾在慕尼黑工业大学的施密德胡伯和多伦多大学的杰弗里·辛顿手下做过博士后[2]。
Quick Facts 艾力克斯·格雷夫斯Alex Graves, 母校 ...
Close
在IDSIA,格雷夫斯通过一种称为连接主义时间分类(CTC)的新方法训练长短期记忆神经网络[3]。这种方法在某些应用中的表现优于传统的语音识别模型[4]。2009年,他的CTC训练的LSTM是第一个赢得模式识别比赛的循环神经网络,并赢得连接手写识别方面的几个比赛[5][6]。这种方法已经变得非常流行。Google在智能手机上使用CTC训练的LSTM进行语音识别[7][8]。
格雷夫斯也是神经图灵机[9]和密切相关的可微分神经计算机的创造者[10][11]。
Alex Graves. Canadian Institute for Advanced Research. (原始内容存档于1 May 2015).
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.
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).