论文信息 - RECURRENT AND FEEDFORWARD BACKPROPAGATION: PERFORMANCE STUDIES

RECURRENT AND FEEDFORWARD BACKPROPAGATION: PERFORMANCE STUDIES

Based on a unified description of neural algorithms for time independent pattern recognition, we discuss the generalization abilities of 3-layer perceptrons for recurrent and feedforward backpropagation, as well as their suitability for implementation on multiprocessor systems.

Bernd Schürmann | H. Behrens | D. Gawronska | J. Hollatz

[1] U. Ramacher,et al. Unified Description of Neural Algorithms for Time-Independent Pattern Recognition , 1991 .

[2] Bernd Schürmann,et al. The `detailed balance' net: a stable asymmetric artificial neural system for unsupervised learning , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

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

[4] Fernando J. Pineda,et al. Generalization of Back propagation to Recurrent and Higher Order Neural Networks , 1987, NIPS.

[5] Luís B. Almeida,et al. A learning rule for asynchronous perceptrons with feedback in a combinatorial environment , 1990 .

[6] Barak A. Pearlmutter. Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.