A unified formalism for neural net training algorithms

The authors present a framework which provides both a unified formalism for describing many connectionist algorithms and a formal definition of the goal of learning for these algorithms. This formal approach is illustrated through several examples from among the classical connectionist literature. Many nonconnectionist systems also fall into this formulation which is thus very general and has several consequences on the design of connectionist systems. For example it allows the training of optimally hybrid architectures where different connectionist or classical modules interact.<<ETX>>

[1]  P. GALLINARI,et al.  On the relations between discriminant analysis and multilayer perceptrons , 1991, Neural Networks.

[2]  Younès Bennani,et al.  Validation of neural net architectures on speech recognition tasks , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[3]  H. Bourlard,et al.  Links Between Markov Models and Multilayer Perceptrons , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  M. Niranjan,et al.  Generalising the nodes of the error propagation network , 1989, International 1989 Joint Conference on Neural Networks.

[5]  Sylvie Thiria,et al.  Cooperation of neural nets for robust classification , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[6]  Patrick Gallinari,et al.  A Framework for the Cooperation of Learning Algorithms , 1990, NIPS.

[7]  Bernard Widrow,et al.  Adaptive switching circuits , 1988 .

[8]  Bernard Angéniol,et al.  Self-organizing feature maps and the travelling salesman problem , 1988, Neural Networks.

[9]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[10]  Kumpati S. Narendra,et al.  Adaptation and learning in automatic systems , 1974 .

[11]  Hervé Bourlard.  HOW CONNECTIONIST MODELS COULD IMPROVE MARKOV MODELS FOR SPEECH RECOGNITION , 1990 .

[12]  Patrick Gallinari,et al.  Learning vector quantization, multi layer perceptron and dynamic programming: comparison and cooperation , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.