Although artificial neural networks can represent a variety of complex systems with a high degree of accuracy, these connectionist models are difficult to interpret. This significantly limits the applicability of neural networks in practice, especially where a premium is placed on the comprehensibility or reliability of systems. A novel artificial neural-network decision tree algorithm (ANN-DT)...

Research on improving the performance of feedforward neural networks has concentrated mostly on the optimal setting of initial weights and learning parameters, sophisticated optimization techniques, architecture optimization, and adaptive activation functions. An alternative approach is presented in this paper where the neural network dynamically selects training patterns from a candidate train...

ground vibrations caused by blasting are undesirable results in the mining industry and can cause serious damage to the nearby buildings and facilities; therefore, controlling such vibrations has an important role in reducing the environmental damaging effects. controlling vibration caused by blasting can be achieved once peak particle velocity (ppv) is predicted. in this paper, the values of p...

abstract forecasting electrical energy demand and consumption is one of the important decision-making tools in distributing companies for making contracts scheduling and purchasing electrical energy. this paper studies load consumption modeling in hamedan city province distribution network by applying esn neural network. weather forecasting data such as minimum day temperature, average day temp...

— Neural networks are usually trained on all available data. Support Vector Machines start from all data but near the end of the training use only a small subset of vectors near the decision border. The same learning strategy may be used in neural networks, independently of the actual optimization method used. Feedforward step is used to identify vectors that will not contribute to optimization...

In this paper, we propose a genetic algorithm based design procedure for a radial-basis function neural network. A Hierarchical Rank Density Genetic Algorithm (HRDGA) is used to evolve both the neural network’s topology and parameters. In addition, the rank-density based fitness assignment technique is used to optimize the performance and topology of the evolved neural network to deal with the ...

Both neural networks and decision trees are popular machine learning methods and are widely used to solve problems from diverse domains. These two classifiers are commonly used base classifiers in an ensemble framework. In this paper, we first present a new variant of oblique decision tree based on a linear classifier, then construct an ensemble classifier based on the fusion of a fast neural n...

Deep Neural Networks are built to generalize outside of training set in mind by using techniques such as regularization, early stopping and dropout. But considerations to make them more resilient to adversarial examples are rarely taken. As deep neural networks become more prevalent in mission critical and real time systems, miscreants start to attack them by intentionally making deep neural ne...

Graph Neural Networks (GNNs) are a new and increasingly popular family of deep neural network architectures to perform learning on graphs. Training them efficiently is challenging due the irregular nature graph data. The problem becomes even more when scaling large graphs that exceed capacity single devices. Standard approaches distributed DNN training, such as data model parallelism, do not di...