Deodhare, Dipti and Vidyasagar, M and Keerthi, Sathiya S (1998) Synthesis of Fault-Tolerant Feedforward Neural Networks Using Minimax Optimization. In: IEEE Transactions on Neural Networks, 9 (5). pp. 891-900.
In this paper we examine a technique by which fault tolerance can be embedded into a feedforward network leading to a network tolerant to the loss of a node and its associated weights. The fault tolerance problem for a feedforward network is formulated as a constrained minimax optimization problem. Typo different methods are used to solve it. In the first method, the constrained minimax optimization problem is converted to a sequence of unconstrained least-squares optimization problems, whose solutions converge to the solution of the original minimax problem. An efficient gradient-based minimization technique, specially tailored for nonlinear least-squares optimization, is then applied to perform the unconstrained minimization at each step of the sequence. Several modifications are made to the basic algorithm to improve its speed of convergence. In the second method a different approach is used to convert the problem to a single unconstrained minimization problem whose solution very nearly equals that of the original minimax problem. Networks synthesized using these methods, though not always fault tolerant, exhibit an acceptable degree of partial fault tolerance.
|Item Type:||Journal Article|
|Additional Information:||©1998 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.|
|Keywords:||Fault tolerance;Minimax optimization|
|Department/Centre:||Division of Electrical Sciences > Computer Science & Automation (Formerly, School of Automation)|
|Date Deposited:||25 Aug 2008|
|Last Modified:||19 Sep 2010 04:15|
Actions (login required)