论文信息 - GRADSIM: A Connectionist Network Simulator Using Gradient Optimization Techniques

GRADSIM: A Connectionist Network Simulator Using Gradient Optimization Techniques

A simulator for connectionist networks which uses gradient methods of nonlinear optimization for network learning is described. The simulator (GRADSIM) was designed for temporal flow model connectionist networks. The complete gradient is computed for networks of general connectivity, including recurrent links. The simulator is written in C, uses simple network and data descriptors for flexibility, and is easily modified for new applications. A version of the simulator which precompiles the network objective function and gradient computations for greatly increased processing speed is also described. Benchmark results for the simulator running on the DEC VAX 8650, SUN 3/260 and CYBER 205 are presented. Comments University of Pennsylvania Department of Computer and Information Science Technical Report No. MSCIS-88-16. This technical report is available at ScholarlyCommons: http://repository.upenn.edu/cis_reports/626 GRADSIM: A CONNECTIONIST NETWORK SIMULATOR USING GRADIENT OPTIMIZATION TECHNIQUES Raymond L. Watrous MS-CIS-88-16 LlNC LAB 103 Department of Computer and Information Science School of Engineering and Applied Science University of Pennsylvania Philadelphia, PA 191 04

Raymond L. Watrous

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

[2] Lokendra Shastri,et al. Learning Phonetic Features Using Connectionist Networks , 1987, IJCAI.

[3] Lokendra Shastri,et al. Learned phonetic discrimination using connectionist networks , 1990, ECST.

[4] P. Werbos,et al. Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[5] Roger Fletcher,et al. A Rapidly Convergent Descent Method for Minimization , 1963, Comput. J..

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

[7] Raymond L. Watrous,et al. Complete gradient optimization of a recurrent network applied to /b/,/d/,/g/ discrimination , 1988 .

[8] Raymond L. Watrous. Learning Algorithms for Connectionist Networks: Applied Gradient Methods of Nonlinear Optimization , 1988 .

[9] J. D. Pearson. ON VARIABLE METRIC METHODS OF MINIMIZATION , 1968 .

[10] R. Fletcher. Practical Methods of Optimization , 1988 .

[11] T. M. Williams,et al. Practical Methods of Optimization. Vol. 1: Unconstrained Optimization , 1980 .

[12] C. G. Broyden. The Convergence of a Class of Double-rank Minimization Algorithms 2. The New Algorithm , 1970 .

[13] M. J. Kascic,et al. Vector Processing on the CYBER 200 , 1980, Angew. Inform..

[14] R. Fletcher,et al. A New Approach to Variable Metric Algorithms , 1970, Comput. J..