摘要: Deep Learning's recent successes have mostly relied on Convolutional Networks, which exploit fundamental statistical properties of images, sounds and video data: the local …
Yoshua Bengio, Nicolas L. Roux, Marc Joliveau, Balázs Kégl, Pascal Lamblin, Learning the 2-D Topology of Imagesneural information processing systems. ,vol. 20, pp. 841- 848 ,(2007)
Andrew Y. Ng, Jiquan Ngiam, Quoc V. Le, Zhenghao Chen, Pang W. Koh, Daniel Chia, Tiled convolutional neural networksneural information processing systems. ,vol. 23, pp. 1279- 1287 ,(2010)
Geoffrey Hinton, Tara Sainath, Brian Kingsbury, Vincent Vanhoucke, Andrew Senior, Navdeep Jaitly, Li Deng, Dong Yu, Abdel-rahman Mohamed, George Dahl, Patrick Nguyen, Deep Neural Networks for Acoustic Modeling in Speech RecognitionIEEE Signal Processing Magazine. ,vol. 29, pp. 82- 97 ,(2012)