Recently, both supervised and unsupervised deep learning techniques have accomplished notable results in various fields. However neural networks with back-propagation are liable to trapping at local minima. Genetic algorithms have been popular as a class of optimization techniques which are good at exploring a large and complex space in an intelligent way to find values close to the global opti...

| This paper describes several algorithms, mapping the back propagation learning algorithm onto a large 2-D torus architecture. To obtain high speedup, we have suggested an approach to combine the possible parallel aspects (training set parallelism, node parallelism and pipelining of training patterns) of the algorithm. Several algorithms were implemented on a 512 processor Fujitsu AP1000 and c...

A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented. The technique is applicable to a wide variety of classiiac-tion functions, including Perceptrons, polyno-mials, and Radial Basis Functions. The effective number of parameters is adjusted automatically to match the complexity of the problem. The solution is expressed as a linear c...

The paper proposes a dynamic programming algorithm for training of functional networks. The algorithm considers each node as a state. The problem is formulated as finding the sequence of states which minimizes the sum of the squared errors approximation. Each node is optimized with regard to its corresponding neural functions and its estimated neuron functions. The dynamic programming algorithm...

this paper extends the sequential learning algorithm strategy of two different types of adaptive radial basis function-based (rbf) neural networks, i.e. growing and pruning radial basis function (gap-rbf) and minimal resource allocation network (mran) to cater for on-line identification of non-linear systems. the original sequential learning algorithm is based on the repetitive utilization of s...

The paper presents a fast codebook training algorithm for vector quantisation. It uses an elimination rule, based on triangular inequality criteria, as well as the partial distortion elimination method, to relieve the computational burden of a conventional codebook training algorithm, including a binary codeword splitting algorithm for the initial codebook and the LBG recursive algorithm. Over ...

~ Recently, a minimum classification error training algorithm has been proposed for minimizing the misclassification probability based on a given set of training samples using a generalized probabilistic descent method. This algorithm is a type of discriminative learning algorithm. but it approaches the objective of nlininlumclassification error in a more direct manner than the conventional dis...