Optimality of Pocket Algorithm
نویسنده
چکیده
Many constructive methods use the pocket algorithm as a basic component in the training of multilayer perceptrons. This is mainly due to the good properties of the pocket algorithm confirmed by a proper convergence theorem which asserts its optimality. Unfortunately the original proof holds vacuously and does not ensure the asymptotical achievement of an optimal weight vector in a general situation. This inadequacy can be overcome by a different approach that leads to the desired result. Moreover, a modified version of this learning method, called pocket algorithm with ratchet, is shown to obtain an optimal configuration within a finite number of iterations independently of the given training set.
منابع مشابه
Degree of Optimality as a Measure of Distance of Power System Operation from Optimal Operation
This paper presents an algorithm based on inter-solutions of having scheduled electricity generation resources and the fuzzy logic as a sublimation tool of outcomes obtained from the schedule inter-solutions. The goal of the algorithm is to bridge the conflicts between minimal cost and other aspects of generation. In the past, the optimal scheduling of electricity generation resources has been ...
متن کاملOn convergence properties of pocket algorithm
The problem of finding optimal weights for a single threshold neuron starting from a general training set is considered. Among the variety of possible learning techniques, the pocket algorithm has a proper convergence theorem which asserts its optimality. However, the original proof ensures the asymptotic achievement of an optimal weight vector only if the inputs in the training set are integer...
متن کاملIs Pocket algorithm optimal?
Most learning algorithms for single neuron are not able to provide for any classification problem the weight vector which satisfies the maximum number of input-output relations contained in the training set. An important exception is given by the pocket algorithm: it repeatedly executes the perceptron algorithm and maintains (in the pocket) the weight vector which is remained unchanged for the ...
متن کاملOptimality of the flexible job shop scheduling system based on Gravitational Search Algorithm
The Flexible Job Shop Scheduling Problem (FJSP) is one of the most general and difficult of all traditional scheduling problems. The Flexible Job Shop Problem (FJSP) is an extension of the classical job shop scheduling problem which allows an operation to be processed by any machine from a given set. The problem is to assign each operation to a machine and to order the operations on the machine...
متن کاملOptimality of the flexible job shop scheduling system based on Gravitational Search Algorithm
The Flexible Job Shop Scheduling Problem (FJSP) is one of the most general and difficult of all traditional scheduling problems. The Flexible Job Shop Problem (FJSP) is an extension of the classical job shop scheduling problem which allows an operation to be processed by any machine from a given set. The problem is to assign each operation to a machine and to order the operations on the machine...
متن کامل