Chandru, V and Dattasharma, A and Keerthi, SS and Sancheti, NK and Vinay, V (1995) Algorithms for the optimal loading of recursive neural nets. In: of Sixth Annual ACMSIAM Symposium on Discrete Algorithms, 2224 Jan. 1995, San Francisco, CA, USA, pp. 342349.

PDF
p342chandru.pdf Download (896Kb) 
Abstract
The authors address the problem of choosing synaptic weights in a recursive (Hopfield) neural network so as to “optimize�? the performance of the network on the recognition of binary strings. The problem has been called the net loading (or learning) problem in the literature. The objective is to maximize the basins of attraction around the desired fixed points (binary strings) of the net. It is known that it is NPhard to evaluate even the twostep radius of attraction of a recursive neural net. They focus on the radius of direct (onestep) attraction and refer to this as the loading problem. They have both theoretical and computational results on this problem: a proof that the net loading problem can be solved in polynomial time using linear programming techniques. This resolves a standing problem in the complexity of recursive neural networks; an alternate formulation of the net loading problem as a proximity problem in highdimensional convex geometry; the design and implementation of a hybrid algorithm for the said proximity problem; successful solution of large scale test problems including the optimal solution to a 900×900 Hopfield net with approximately $4X10^5$ synaptic weights. It may be noted that the experiments indicate that the radius of direct attraction is actually a very good proxy of the intractable (multistep) radius of attraction. In all the test problems that they have solved, the synaptic weights obtained as a a solution to the maximum radius of direct attraction also maximize the radius of (multistep) attraction
Item Type:  Conference Paper 

Related URLs:  
Additional Information:  Copyright of this article belongs to ACM 
Keywords:  computational complexity;Hopfield neural nets;linear programming 
Department/Centre:  Division of Electrical Sciences > Computer Science & Automation (Formerly, School of Automation) 
Date Deposited:  17 Sep 2007 
Last Modified:  19 Sep 2010 04:37 
URI:  http://eprints.iisc.ernet.in/id/eprint/10889 
Actions (login required)
View Item 