Neural networks with step activation function can be very efficient ways of performing non linear mappings. However, no standard learning algorithm exists for training this kind of neural networks. In this work we use Genetic Programming (GP) to discover supervised learning algorithms which can train neural networks with step activation function. Thanks to GP, a new learning algorithm has been ...

Transfer Learning is a paradigm in machine learning to solve a target problem by reusing the learning with minor modifications from a different but related source problem. In this paper we propose a novel feature transference approach, especially when the source and the target problems are drawn from different distributions. We use deep neural networks to transfer either low or middle or higher...

This paper explores the potential of extreme learning machine based supervised classification algorithm for land cover classification. In comparison to a backpropagation neural network, which requires setting of several user-defined parameters and may produce local minima, extreme learning machine require setting of one parameter and produce a unique solution. ETM+ multispectral data set (Engla...

The rapid progress in artificial intelligence in recent years can largely be attributed to the resurgence of neural networks, which enables learning representations in an end-to-end manner. Although neural network are powerful, they have many limitations. For examples, neural networks are computationally expensive and memory inefficient; Neural network training needs many labeled exampled, espe...

Network security analysis based on attack graphs has been applied extensively in recent years. The ranking of nodes in an attack graph is an important step towards analyzing network security. This paper proposes an alternative attack graph ranking scheme based on a recent approach to machine learning in a structured graph domain, namely, Graph Neural Networks (GNNs). Evidence is presented in th...

Problem statement: Constructive neural network learning algorithms provide optimal ways to determine the architecture of a multi layer perceptron network along with learning algorithms for determining appropriate weights for pattern classification problems. These algorithms initially start with small network and dynamically allow the network to grow by adding and training neurons as needed unti...

In this paper, both truth and falsity inputs are used to trained neural networks. Falsity input is the complement of the truth input. Two pairs of neural networks are created. The first pair of neural networks are trained using the truth input whereas the second pair of neural networks are trained using the falsity input. Each pair of neural networks are trained to predict degree of truth and d...

Modelling and forecasting Stock market is a challenging task for economists and engineers since it has a dynamic structure and nonlinear characteristic. This nonlinearity affects the efficiency of the price characteristics. Using an Artificial Neural Network (ANN) is a proper way to model this nonlinearity and it has been used successfully in one-step-ahead and multi-step-ahead prediction of di...

reservoir permeability is a critical parameter for characterization of the hydrocarbon reservoirs. in fact, determination of permeability is a crucial task in reserve estimation, production and development. traditional methods for permeability prediction are well log and core data analysis which are very expensive and time-consuming. well log data is an alternative approach for prediction of pe...

The forecast of fluctuations and prices is the major concern in financial markets. Thus, developing an accurate and robust forecasting decision model is critically favorable to the investors. As gold has shown a special capability to smooth inflation fluctuations, governors use gold as a price controlling lever. Thus, more information about future gold price trends will help to make the firm de...