Assessment of the quality of neural network models based on a multifactorial information criterion. Oleksandr O. Fomin, Valentyn A. Krykun (Herald of Advanced Information Technology, Vol. 7 No. 1) (original) (raw)
Related papers
Performance measures, consistency, and power for artificial neural network models
Mathematical and Computer Modelling, 1995
building in artificial neural networks (ANN) refers to selecting the "optimal" network architecture, network topology, data representation, training algorithm, training parameters, and terminating criteria, such that some desired level of performance is achieved. Validation, a critical aspect of any model construction, is based upon some specified ANN performance measure of data that was not used in model construction.
Competitive Analysis of different Artificial Neural Network Models
International Journal of Scientific Research in Education, 2017
In this paper, three different models for classification of nonlinear problems, i.e., Spiking Neuron Model, Multiplicative Neuron Model and Multilayer Perceptron Model have been taken for analysis. The well known, Ex-OR problem is been taken for the comparative analysis of the above three Artificial Neural Network models. It was found that spiking neuron model can be considered the best model in context of various parameters of Artificial Neural Network like learning rate, execution time, number of iteration, time elapse in training etc. Further, Iris data set (ref: www.lib.uci.edu ) has been taken for the analysis using above three ANN models. Comparing the various parameters learning rate, execution time, number of iteration, time elapse in training etc. it was observed that learning rate, execution time, number of iteration, time elapse in training is minimum in the case of spiking neuron model. On the basis of analysis it can be said that spiking neuron model can be taken as bes...
Neural Networks, IEEE …, 1994
The problem of model selection, or determination of the number of hidden units, can be approached statistically, by generalizing Akaike's information criterion (AIC) to be applicable to unfaithful (i.e., unrealizable) models with general loss criteria including regularization terms. The relation between the training error and the generalization error is studied in terms of the number of the training examples and the complexity of a network which reduces to the number of parameters in the ordinary statistical theory of the AIC. This relation leads to a new Network Information Criterion (NIC) which is useful for selecting the optimal network model based on a given training set. 1045-9227/94$04.00 0 1994 IEEE Authorized licensed use limited to: University of Minnesota. Downloaded on June 21,2010 at 15:16:55 UTC from IEEE Xplore. Restrictions apply.
IJERT-Evaluation of Artificial Neural Networks
International Journal of Engineering Research and Technology (IJERT), 2014
https://www.ijert.org/evaluation-of-artificial-neural-networks https://www.ijert.org/research/evaluation-of-artificial-neural-networks-IJERTV1IS7004.pdf Artificial Neural Networks are composed of interconnecting artificial neurons (programming constructs that mimic the properties of biological neurons). Artificial neural networks may either be used to gain an understanding of biological neural networks, or for solving artificial intelligence problems without necessarily creating a model of a real biological system. Artificial Neural Network has been shown to be an efficient tool for non-parametric modeling of data in a variety of different context where the output is non-linear function of prediction, medicines, pattern recognition and image processing. 1. In this paper we present neural network architecture for learning of robotic grasping tasks. Systematic computer simulations have been carried out in order to test learning and generalization capabilities of the system. The proposed model can be used as a high level controller for a robotic dexterous hand during learning and execution of grasping tasks. 2. Diagnosis of diseases is well known problem in the medical field. Past research shows that medical database of disease can be train by using various neural network models. Many medical problems face the problem of curse of dimensionality due to the excessively large number of input attributes. Breast cancer is one such problem. Breast cancer is the second leading cause of cancer deaths worldwide and occurs in one out of eight women. In this paper we develop a system for diagnosis, prognosis and prediction of breast cancer using Artificial Neural Network (ANN) models. 2. Introduction Artificial neural networks are a computational tool, based on the properties of biological neural systems. Neural networks excel in a number of problem areas where conventional von Neumann computer systems have traditionally been slow and inefficient. This book is going to discuss the creation and use of artificial neural networks.Over the last few years, a number of studies were reported concerning machine learning, and how it has been applied to help robots to improve their operational capabilities. Robots must be able to understand the structure of this environment. To reach their targets without collisions, the robots must be endowed with perception, data processing, recognition, learning, reasoning, interpreting, and decision-making and action capacities. The ability to acquire these faculties to treat and transmit knowledge constitutes the key of a certain kind of artificial intelligence. Reproduce this kind of intelligence is, up to now, a human ambition in the construction and development of intelligent machines, and particularly autonomous mobile robots. An Artificial Neural Network (ANN), usually called neural network (NN), is a mathematical model or computational model that is inspired by the structure and/or functional aspects of biological neural networks. A neural network consists of an interconnected group of artificial neurons, and it processes information using a connectionist approach to computation. In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network
Searching Most Efficient Neural Network Architecture Using Akaike's Information Criterion (AIC)
International Journal of …, 2010
The problem of model selection is considerably important for acquiring higher levels of generalization capability in supervised learning. Neural networks are commonly used networks in many engineering applications due to its better generalization property. An ensemble neural network algorithm is proposed based on the Akaike information criterion (AIC). Ecologists have long relied on hypothesis testing to include or exclude variables in models, although the conclusions often depend on the approach used. The advent of methods based on information theory, also known as information-theoretic approaches, has changed the way we look at model selection The Akaike information criterion (AIC) has been successfully used in model selection. It is not easy to decide the optimal size of the neural network because of its strong nonlinearity. We discuss problems with well used information and propose a model selection method.
An Innovative Artificial Neural Network Evaluation Model: Application in industry
2000
Monitoring of processing elements values and overall performance is one of the most critical issues of an Artificial Neural Network development process. This should happen as the network evolves and it is the actual task that enables the developer to make informed decisions about the proper network topology, math functions, training times and learning parameters. This manuscript presents the framework
COMPARISON AND ANAYSIS OF ANN BASED INTELLIGENT SYSTEMS
In new emerging techniques of information technology, neural network is also one. Now we see some information's about the neural network. The power and usefulness of artificial neural networks have been demonstrated in several applications including speech synthesis, diagnostic problems, medicine, business and finance, robotic control, signal processing, computer vision and many other problems
Characteristics of an Artificial Neural Network and its use in Business
International Journal for Research in Engineering Application & Management , 2018
Improvements in compute power over the years has helped mathematicians and computer scientist to mainstream complex mathematical models and prediction for business. One such method is using Artificial Neural Networks (ANN) which is helping business community to augment their abilities to predict business outcomes. Current researches in ANN has led to significant progress in understanding customer behaviour, financial risk, prevent fraud among many others. A significant role has also been played by cloud computing companies like Amazon, IBM, Microsoft together with open source initiatives of organizations like Apache Foundation, Google etc., has helped the cause of the erstwhile business manager who were otherwise were having limited tools to predict, say, sales for the next quarter.. In this paper, we describe the basics of an artificial neural networks and its usage in businesses.