====== Convolutional Networks ====== ===== Time Delay Neural Networks ===== {{tdnn-simple.png?220 }} During the first years of my thesis, my main thema was the construction of speech recognition systems using neural networks. Kevin Lang and Geoff Hinton had published a tech report describing Time-Delay Neural Networks (TDNN). Alex Waibel and his team then demonstrated their efficiency at discriminating the japanese phonems /b/, /d/, /g/. But their approach was very costly. Training took weeks on their Alliant super-computer. Using [[stochastic|Stochastic Gradient Descent]], I proposed a new and computationally efficient variant of Time-Delay Neural Networks. I was able to run speaker-independent word recognition systems on a regular workstation instead of a super-computer. This was later extended to continuous speech recognition system by combining a time-delay neural network and a Viterbi decoder. The combination was trained globally using a discriminant algorithm. ===== Convolutional Networks for Computer Vision ===== {{ invar.png?220}} This work led to a long collaboration with [[http://yann.lecun.com|Yann LeCun]] on convolutional networks applied to a broad variety of problems in image recognition and signal processing, using increasingly sophisticated [[structured|Structured Learning]] techniques. See also Yann's pages about [[http://www.cs.nyu.edu/~yann/research|convolutional networks]]. \\ \\ ===== Publications ===== Léon Bottou: **Reconnaissance de la parole par reseaux connexionnistes**, //Proceedings of Neuro Nimes 88//, 197-218, Nimes, France, 1988. [[:papers:bottou-88b|more...]] Léon Bottou, Françoise. Fogelman Soulié, Pascal Blanchet and Jean Sylvain Lienard: **Experiments with Time Delay Networks and Dynamic Time Warping for Speaker Independent Isolated Digit Recognition**, //Proceedings of EuroSpeech 89//, 2:537-540, Paris, France, 1989. [[:papers:bottou-89|more...]] M.D. Bedworth, L. Bottou, J. S. Bridle, F. Fallside, L. Flynn, F. Fogelman Soulié, K.M. Ponting and R.W. Prager: **Comparison of neural and conventional classifiers on a speech recognition problem**, //Proceedings of IEE 1st International Conference on Artificial Neural Networks//, London, 1989. [[:papers:bedworth-89|more...]] Xavier Driancourt and Léon Bottou: **TDNN-Extracted features**, //Proceedings of Neuro Nimes 90//, EC2, Nimes, France, 1990. [[:papers:driancourt-bottou-90|more...]] Léon Bottou, Françoise Fogelman Soulié, Pascal Blanchet and Jean Sylvain Lienard: **Speaker independent isolated digit recognition: Multilayer perceptron vs Dynamic Time Warping**, //Neural Networks//, 3:453-465, 1990. [[:papers/bottou-90|more...]] Léon Bottou: //**Une Approche théorique de l'Apprentissage Connexionniste: Applications à la Reconnaissance de la Parole**//, Orsay, France, 1991. [[:papers/bottou-91a|more...]] Xavier Driancourt, Léon Bottou and Patrick Gallinari: **Learning Vector Quantization, Multi Layer Perceptron and Dynamic Time Warping: Comparison and Cooperation**, //Proceedings of the International Joint Conference on Neural Networks//, Seattle, 1991. [[:papers/driancourt-bottou-91|more...]] Jame Bromley, Jim W. Bentz, Léon Bottou, Isabelle Guyon, Yann Le Cun, C. Moore, Eduard Säckinger and Roopak Shah: **Signature Verification using a Siamese Time Delay Neural Network**, //International Journal of Pattern Recognition and Artificial Intelligence//, 7(4), 1993. [[papers/bromley-bentz-93|more...]] Léon Bottou, Corinna Cortes, John S. Denker, Harris Drucker, Isabelle Guyon, Lawrence D. Jackel, Yann Le Cun, Urs A. Muller, Eduard Säckinger, Patrice Simard and Vladimir Vapnik: **Comparison of classifier methods: a case study in handwritten digit recognition**, //Proceedings of the 12th IAPR International Conference on Pattern Recognition, Conference B: Computer Vision & Image Processing.//, 2:77-82, IEEE, Jerusalem, October 1994. [[papers/bottou-cortes-94|more...]] Yann Le Cun, Léon Bottou, Yoshua Bengio and Patrick Haffner: **Gradient Based Learning Applied to Document Recognition**, //Proceedings of IEEE//, 86(11):2278-2324, 1998. [[papers/lecun-98h|more...]] Yann LeCun, Léon Bottou and Jie HuangFu: **Learning Methods for Generic Object Recognition with Invariance to Pose and Lighting**, //Proc. of Computer Vision and Pattern Recognition//, IEEE, Washington, D.C., 2004. [[papers/lecun-bottou-huangfu-2004|more...]]