Signal-flow-graph derivation of on-line gradient learning algorithms

IEEE International Conference on Neural Networks - Conference Proceedings

Volumn 3, Issue , 1997, Pages 1884-1889

  Campolucci, P ^a   Marchegiani, A ^a   Uncini, A ^a   Piazza, F ^a  

^a Dipartimento di Elettronica Ed Automatica   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

GENERAL METHOD; GRADIENT COMPUTATION; GRADIENT LEARNING ALGORITHM; NON-LINEAR DYNAMIC SYSTEMS; OFF-LINE LEARNING; ONLINE TRAINING; RECURRENT NETWORKS; SYSTEM OUTPUT;

COMPUTER SIMULATION; COST FUNCTIONS; DYNAMICAL SYSTEMS; NONLINEAR DYNAMICAL SYSTEMS; RECURRENT NEURAL NETWORKS; COMPUTATIONAL METHODS; LEARNING ALGORITHMS; LEARNING SYSTEMS; NONLINEAR CONTROL SYSTEMS; ONLINE SYSTEMS;

SIGNAL FLOW GRAPHS; FEEDFORWARD NEURAL NETWORKS;

BACKWARD GRADIENT COMPUTATION; MEAN SQUARE ERROR COST FUNCTION; SIGNAL FLOW GRAPH (SFG) REPRESENTATION;

EID: 0030650652     PISSN: 10987576     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICNN.1997.614186     Document Type: Conference Paper

References (12)

1. R.J. Williams, J. Peng, "An efficient gradient-based algorithm for on line training of recurrent network trajectories", Neural Computation 2:490-501, 1990.
2. R.J. Williams, D. Zipser, "A Learning Algorithm for Continually Running Fully Recurrent Neural Networks", Neural Computation 1: 270-280, 1989.
3. A.D. Back, A.C. Tsoi, "FIR and IIR synapses, a new neural network architecture for time series modelling", Neural Computation 3: 375-385, 1991.
4. A.C. Tsoi, A.D. Back, "Locally recurrent globally feedforward networks: a critical review of architectures", IEEE Transactions on Neural Networks, vol. 5, no. 2, 229-239, March 1994.
5. A.D. Back, A.C. Tsoi, "A simplified gradient algorithm for IIR synapse Multilayer Perceptron", Neural Computation 5:456-462, 1993.
6. P. Campolucci, F. Piazza, A. Uncini, "On-line learning algorithms for neural networks with IIR synapses", Proc. of the IEEE International Conference of Neural Networks, Perth, Nov. 1995.
7. P. Campolucci, A. Uncini, F. Piazza, "Causal Back Propagation Through Time for Locally Recurrent Neural Networks", Proc. of the IEEE International Symposium on Circuits and Systems, Atlanta, May 1996.
8. B. Srinivasan, U.R. Prasad and N.J. Rao, "Backpropagation through Adjointsfor the identification ofNon linear Dynamic Systems using Recurrent Neural Models", IEEE Trans, on Neural Networks pp. 213-228, March 1994.
9. E.A.Wan, F.Beaufays, "Diagrammatic Derivation of Gradient Algorithms for Neural Networks", Neural Computation 8: 182-201, 1996.
10. A.Y.Lee, "Signal Flow Graphs-Computer-Aided System Analysis and Sensitivity Calculations", IEEE Transactions on Circuits and Systems, vol. cas-21, NO. 2, pp. 209-216, March 1974.
11. O.Nerrand, P.Roussel-Ragot, L.Personnaz, G.Dreyfus, S.Marcos, "Neural Networks and Nonlinear Adaptive Filtering: Unifying Concepts and New Algorithms", Neural Computation 5: 165-199, 1993.
12. K.S. Narendra, K. Parthasarathy, "Gradient Methods for the Optimization of Dynamical Systems Containing Neural Networks", IEEE Trans, on Neural Networks, vol. 2, no. 2, March 1991.