A Deep Comparative Study between Different Neural Networks Classifiers

In Machine learning and artificial intelligence have seemingly never been as typical and relevant to real-time applications as they are in these days autonomous, big data era. The fortune of machine learning and artificial intelligence depends on the coexistence of three important conditions powerful computing environments, rich and/or large data, and efficient learning techniques (algorithms). The Extreme Learning Machine (ELM) as an emerging learning method provides efficient unified solutions to generalized feed-forward networks including but not limited to (both single- and multi-hidden-layer) neural networks, radial basis function (RBF) networks, and kernel learning. The widely used supervised neural network is the Support Vector Machine (SVM). It is known as being very accurate but at the expenditure of high computational complexity, particularly in the learning phase, making it less appropriate for hardware-oriented applications. A deep belief network (DBN) is an originative graphical model, or alternatively a type of deep neural network, composed of multiple layers of latent variables (hidden units), with connections between the layers but not between units within each layer. In this paper a new comparative study is proposed on different neural networks classifiers. The technique is implemented for accuracy of different algorithms.