Gradient-based learning applied to document recognition

DMCA

Gradient-based learning applied to document recognition (1998)

Cached

Download Links

by Yann Lecun , Léon Bottou , Yoshua Bengio , Patrick Haffner

Venue:	Proceedings of the IEEE
Citations:	1528 - 84 self

Citations

13212	Statistical Learning Theory - Vapnik - 1998
5881	A tutorial on hidden markov models and selected applications in speech recognition - Rabiner - 1989
3696	Learning internal representations by error propagation - Rumelhart, Hinton, et al. - 1986
1863	A training algorithm for optimal margin classifiers - Boser, Guyon, et al. - 1992
1653	Error bounds for convolutional codes and an asymptotically optimal decoding algorithm - Viterbi - 1967
1309	Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex - Hubel, Wiesel - 1962
1248	Approximation by superpositions of a sigmoidal function", - Cybenko - 1989
1206	Neural networkbased face detection - Rowley, Baluja, et al. - 1998
868	The strength of weak learnability - Schapire - 1990
726	Training Support Vector Machine: An application to Face Detection - Osuna, Freund, et al.
721	Solving multiclass learning problems via errorcorrecting output codes - Dietterich, Bakiri - 1995
584	A learning algorithm for Boltzmann machines - Ackley, Hinton, et al. - 1985
575	Connectionist Speech Recognition: A Hybrid Approach, - Bourlard, Morgan - 1994
473	Backpropagation applied to handwritten zip code recognition - LeCun, Boser - 1989
434	Phoneme Recognition Using Time-Delay Neural Networks", - Waibel, Hanazawa, et al. - 1989
392	Finite-state transducers in language and speech processing, - Mohri - 1997
387	Learning long–term dependencies with gradient descent is difficult - Bengio, Frasconi, et al. - 1994
340	Learning and relearning in Boltzmann machines - Hinton, Sejnowski - 1986
285	Handwritten digit recognition with a back-propagation network - LeCun, Boser, et al. - 1990
277	Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition,‖ Neurocomputing—Algorithms, Architectures and Applications, - Bridle - 1989
272	Efficient pattern recognition using a new transformation distance - Simard, LeCun, et al. - 1994
234	Face Recognition: A Convolutional Neural Network Approach. - Lawrence, Giles, et al. - 1997
228	Discriminative Learning for Minimum Error Classification - Juang, Katagiri - 1992
210	A Time-Delay Neural Network Architecture for Isolated Word Recognition", - Lang, Waibel, et al. - 1990
190	Improving the accuracy and speed of support vector learning machines - Burges, Schölkopf - 1997
158	Local learning algorithm - Bottou, Vapnik - 1992
136	Theory of adaptive pattern classifiers, - Amari - 1967
136	Speech recognition by composition of weighted finite automata. - Pereira, Riley - 1997
126	Neocognitron: a new algorithm for pattern recognition tolerant of deformations and shifts in position. - Fukushima, Miyake - 1982
126	An input output HMM architecture. - Bengio, Frasconi - 1995
114	Comparison of learning algorithms for handwritten digit recognition. - LeCun - 1995
114	Statistical pattern recognition with neural networks: benchmarking studies. In: Anderson J, Pellionisz A, Rosenfeld E (eds) - Kohonen, Barna, et al. - 1989
113	Links between Markov models and multi-layer perceptrons, - Bourlard, Wellekens - 1990
104	Improving Performance in Neural Networks Using a Boosting Algorithm. - Drucker, Schapire, et al. - 1993
102	Computer recognition of unconstrained handwritten numerals”, - Suen, Nadal, et al. - 1992
96	The Perception of Multiple Objects: A Connectioni~t Approach - Mozer - 1991
77	Global optimization of a neural network-hidden Markov model hybrid. Neural Networks - Bengio, Mori, et al. - 1992
61	Une approche theorique de l’apprentissage connexionniste: Applications a la reconnaissance de la parole. Doctoral dissertation, Universite de - Bottou - 1991
60	Design of a Neural Network Character Recognizer, Pattern Recognition - Guyon, Albrecht, et al. - 1990
60	Neural networks for speech and sequence recognition, - Bengio - 1996
59	Signature verification using a “siamese” time delay neural network. - Bromley, Bentz, et al. - 1993
57	Measuring the VC-dimension of a learning machine - Vapnik, Levin, et al. - 1994
56	Cognitron: a self-organizing multilayered neural network - Fukushima - 1975
54	LeRec: A NN/HMM hybrid for on-line handwriting recognition. - Bengio, LeCun, et al. - 1995
53	Integrated segmentation and recognition of hand-printed numerals. In: - Keeler, Rumelhart, et al. - 1990
52	Weighted rational transductions and their application to human language processing. - Pereira, Riley, et al. - 1994
49	Statistical mechanics of learning from examples - Seung, Sompolinsky - 1992
45	Adaptation and Learning in Automatic Systems. - Tsypkin - 1971
45	Multi-digit recognition using a space displacement neural network. - Matan, Burges, et al. - 1993
41	A framework for the cooperation of learning algorithms - Bottou, Gallinari - 1991
38	Learning Processes in an asymmetric threshold network. Disordered Systems and Biological Organization, - LeCun - 1986
36	ªEigenvalues of Covariance Matrices: Application to Neural-Network Learning,º Physical Review Letters, - Cun, Kanter, et al. - 1991
36	Alpha-nets: a recurrent neural network architecture with a hidden Markov model interpretation - Bridle - 1990
35	A theoretical framework for back-propagation - LeCun - 1988
35	Connectionist Viterbi Training: A New Hybrid Method for Continuous Speech Recognition, - Franzini, Lee, et al. - 1990
33	Handwritten digit recognition; application of neural network chips and automatic learning”, - LeCun - 1989
32	A convolutional neural network hand tracker. - Nowlan, Platt - 1995
31	Application of the ANNA neural network chip to high-speed character recognition - Sackinger, Boser, et al. - 1992
30	An Analog Neural Network Processor with Programmable Network Topology - Boser, Sackinger - 1991
29	Word normalization for online handwritten word recognition - Bengio, LeCun - 1994
29	Weighted determinization and minimization for large vocabulary speech recognition,” - Mohri, Riley - 1997
26	Multi-State Time Delay Neural Networks for Continuous Speech Recognition - Haffner, Waibel - 1992
24	Combining Hidden Markov Model and Neural Network Classifiers, - Niles, Silverman - 1990
23	Modeles Connexionnistes de l'Apprentissage - Cun - 1987
23	Centered-Object Integrated Segmentation and Recognition of Overlapping Handprinted - Martin - 1993
22	Recognition-based segmentation of on-line hand-printed words - SCHENKEL, WEISSMAN, et al. - 1993
21	Foundations of the Theory of Learning Systems - Tsypkin - 1973
21	Learning-logic - Parker - 1985
18	A learning scheme for asymmetric threshold networks - LeCun - 1985
18	Shortest path segmentation: a method for training a neural network to recognize character strings - Burges, Matan, et al. - 1992
17	High-performance reading machines - Srihari - 1992
17	Handwritten digit recognition using k-nearest neighbor, radial basis function, and back-propagation neural network - Lee
17	Speaker-independent word recognition using dynamic programming neural networks - Sakoe, Isotani, et al. - 1989
16	Neural-net classifiers useful for speech recognition,” in - Lippmann, Gold - 1987
15	Learning curves: Asymptotic value and rate of convergence - Cortes, Jackel, et al. - 1994
14	Learning in Random Nets’, - Minsky, Selfridge - 1961
13	Reading Checks with Graph Transformer Networks - LeCun, Bottou, et al. - 1997
13	Overview and synthesis of online cursive handwriting recognition techniques - Guyon, Schenkel, et al. - 1997
12	Speech recognition with continuous-parameter hidden Markov models. - Bahl, Brown, et al. - 1987
12	A Multifont Word Recognition System for Postal Address Reading - Schurmann - 1978
11	imum Mutual Information of Hidden Markov Model Parame- ters - Bahl, Brown, et al. - 1986
11	Connectionist Architectural Learning for High Performance Character and - BODENHAUSEN, MANKE, et al. - 1993
11	Original approach for the localization of objects in images - Vaillant, Monrocq, et al. - 1994
9	A system for off-line recognition of handwritten text - Breuel - 1994
9	Postal address block location using a convolutional locator network - Wolf, Platt - 1994
8	Speaker-independent isolated digit recognition: multilayer perceptrons vs. dynamic warping - Bottou, Fogelman, et al. - 1990
8	Combining TDNN and HMM in a Hybrid System for Improved Continuous-Speech Recognition", - Dugast, Aubert - 1994
7	Reading handwritten digits: A zip code recognition system - Matan, Bromley, et al. - 1992
6	Time-Delay Neural Networks Embedding Time Alignment: a Performance Analysis - P, Waibel - 1991
6	Connectionist speech recognition with a global MMI algorithm - Haffner - 1993
5	Dynamics of On-Line Gradient Descent Learning for Multilayer Neural Networks - Saad, Birmingham, et al. - 1996
5	MLP, LVQ and DP: Comparison & cooperation - Driancourt, Bottou, et al. - 1991
5	Discriminative feature and model design for automatic speech recognition - Rahim, Bengio, et al. - 1997
4	Multi-resolution neural networks for omnifont character recognition - Wang, Jean - 1993
4	Comparing Different Neural Net Architectures for Classifying Handwritten Digits - Guyon, Poujaud, et al. - 1989
3	Neural network - Gaussian mixture hybrid for speech recognition or density estimation - Bengio, Mori, et al. - 1992
1	Generalization and network design strategies," in Connectionism in - LeCun - 1989
1	construction of quadratic polynomial classifiers - Ott - 1976
1	Image segmentation and recognition, " in The Mathematics of Induction - Denker, Burges - 1995
1	der Malsburg, "Distortion invariant object recognition in the dynamic link architecture - Lades, Vorbruggen, et al. - 1993