Sort
By YearBy Citation
Add Paper
View All
Claim
Alex GravesCIFAR Junior Fellow
views: 899
Information
CIFAR Junior Fellow
Sign in to view more
Experience
Sign in to view more
Education
Sign in to view more
Bio
Research Interests
Recurrent neural networks (especially LSTM)
Supervised sequence labelling (especially speech and handwriting recognition)
Unsupervised sequence learning
At IDSIA, he trained long-term neural memory networks by a new method called connectionist time classification. In certain applications, this method outperformed traditional voice recognition models. In 2009, his CTC-trained LSTM was the first repeat neural network to win pattern recognition contests, winning a number of handwriting awards.
This is a very popular method. Google uses CTC-trained LSTM for smartphone voice recognition.Graves also designs the neural Turing machines and the related neural computer.
Recurrent neural networks (especially LSTM)
Supervised sequence labelling (especially speech and handwriting recognition)
Unsupervised sequence learning
At IDSIA, he trained long-term neural memory networks by a new method called connectionist time classification. In certain applications, this method outperformed traditional voice recognition models. In 2009, his CTC-trained LSTM was the first repeat neural network to win pattern recognition contests, winning a number of handwriting awards.
This is a very popular method. Google uses CTC-trained LSTM for smartphone voice recognition.Graves also designs the neural Turing machines and the related neural computer.
Research Interests
Papers
Author Statistics
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果，我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问，可以通过电子邮件方式联系我们：report@aminer.cn