With the advancement of Machine Learning, since its beginning and over the last years, a special attention has been given to the Artificial Neural Network. As an inspiration from natural selection of animal groups and human’s neural system, the Artificial Neural Network also known as Neural Networks has become the new computational power which is used for solving real world problems. Neural Networks alone as a concept involve various methods for achieving their success; thus, this review paper describes an overview of such methods called Particle Swarm Optimization, Backpropagation, and Neural Network itself, respectively. A brief explanation of the concepts, history, performances, advantages, and disadvantages is given, followed by the latest researches done on these methods. A description of solutions and applications on various industrial sectors such as Medicine or Information Technology has been provided. The last part briefly discusses the directions, current, and future challenges of Neural Networks towards achieving the highest success rate in solving real world problems.

A spiking neurons network encodes information in the timing of individual spike times. A novel supervised learning rule for SpikeProp is derived to overcome the discontinuities introduced by the spiking thresholding. This algorithm is based on an errorbackpropagation learning rule suited for supervised learning of spiking neurons that use exact spike time coding. The SpikeProp is able to demonstrate the spiking neurons that can perform complex nonlinear classification in fast temporal coding. This study proposes enhancements of SpikeProp learning algorithm for supervised training of spiking networks which can deal with complex patterns. The proposed methods include the SpikeProp particle swarm optimization (PSO) and angle driven dependency learning rate. These methods are presented to SpikeProp network for multilayer learning enhancement and weights optimization. Input and output patterns are encoded as spike trains of precisely timed spikes, and the network learns to transform the input trains into target output trains. With these enhancements, our proposed methods outperformed other conventional neural network architectures.

No abstract

No abstract

Spiking Neural Network (SNN) uses individual spikes in time field to perform as well as to communicate computation in such a way as the actual neurons act. SNN was not studied earlier as it was considered too complicated and too hard to examine. Several limitations concerning the characteristics of SNN which were not researched earlier are now resolved since the introduction of SpikeProp in 2000 by Sander Bothe as a supervised SNN learning model. This paper defines the research developments of the enhancement Spikeprop learning using K-fold cross validation for datasets classification. Hence, this paper introduces acceleration factors of SpikeProp using Radius Initial Weight and Differential Evolution (DE) Initialization weights as proposed methods. In addition, training and testing using K-fold cross validation properties of the new proposed method were investigated using datasets obtained from Machine Learning Benchmark Repository as an improved Bohte’s algorithm. A comparison of the performance was made between the proposed method and Backpropagation (BP) together with the Standard SpikeProp. The findings also reveal that the proposed method has better performance when compared to Standard SpikeProp as well as the BP for all datasets performed by K-fold cross validation for classification datasets.