A Devs-based Ann Training And Prediction Platform.
ABSTRACT
The artificial (AI) domain grows every day with new and architectures. Artificial Neural Networks (ANNs), a of AI has become a very interesting since the eighties when the back-propagation learning algorithm and the feed-forward were first introduced.
As time passed, ANNs were able to solve non-linear problems and were being used in the classification, prediction, and representation of complex systems.
However, ANN uses a black box learning approach – which makes it impossible to interpret the relationship between the input and the output. Discrete Event System Specification (DEVS) is a mathematical well-defined formalism that can b
e used to model dynamic systems in a hierarchical and modular manner; it can automatically generate simulators for the described DEVS models. Combining ANN and DEVS, we can model the complex configuration of ANNs and express its internal workings.
In this thesis, we are extending the DEVS-Based ANN proposed by Toma et al [1] for comparing multiple configuration parameters and learning algorithms.
The DEVS model is described using a visual modeling language known as High-Level Language Specification (HiLLS) for a clear understanding. This approach will help users and algorithm developers to test and compare different algorithm implementations and parameter configurations of ANN.
INTRODUCTION
Modeling and Simulation (M&S), the third pillar of science is a paradigm that provides a way of obtaining the behavior of the representation of an object in real life without doing physical experiments.
As introduced by the theory of Modeling and simulation [2], there are four major important concepts of M&S. The concepts are defined below:
a) System: is a well-defined object in the real world under specific conditions that we are interested in modeling.
b) Experimental Frame (EF): is a specification of the conditions within which the system is observed or experimented. It is realized as a system (with generators, acceptors and transducers) that interacts with the source system to obtain data of interest under specified conditions.
c) Model: is an abstract representation of the structure and properties of a system at some particular point in time or space intended to promote understanding of the real system.
d) Simulation: is the execution of a model over time in order to get information about the changes in the behavior of the system during executions.
Modeling complex systems require a robust formalism. The Discrete Event System Specification (DEVS) formalism [3] that was introduced in the early ’70s is a theoretically well-defined formalism for modeling discrete event systems in a hierarchical and modular manner.
It allows the behavior modeling of complex systems. Artificial Neural Networks (ANN) is a branch of artificial intelligence that became popular in the eighties when the back-propagation algorithm [4] for multilayer feed-forward architectures was introduced.
It is widely known that classical neural networks, even with one hidden layer, are universal function approximators [5]. ANNs became widely applicable for real applications when it had the capabilities to solve non-linear problems.
It is used for modeling of complex optimization problems such as classification, prediction and pattern recognition. 2 Artificial neural networks is capable of modeling complex non-linear systems using adaptive learning mechanism to derive meaning from complicated or imprecise data with a high degree of accuracy.
REFERENCES
S. Toma, L. Capocchi, D. Federici, and others, “A New DEVS-Based Generic Artificial
Neural Network Modeling Approach,” Proceeding EMSS 2011, 2011.
B. P. Zeigler, H. Praehofer, and T. G. Kim, Theory of modeling and simulation: integrating
discrete event and continuous complex dynamic systems. Academic press, 2000.
B. P. Zeigler, Theory of modeling and simulation. New York: Wiley-Interscience, 1976.
D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by backpropagating errors,” Nature, vol. 323, pp. 533 – 536, 1986.
K. Hornik, M. Stinchcombe, and H. White, “Multilayer feedforward networks are universal
approximators,” Neural Netw., vol. 2, no. 5, pp. 359–366, 1989.
H. O. Aliyu, O. Maïga, H. I. Abdulwahab, and M. K. Traoré, “High Level Language for
System Specification.”
M. K. Traoré, “A graphical notation for DEVS,” in Proceedings of the 2009 Spring
Simulation Multiconference, 2009, p. 162.
S. H. Jung and T. G. Kim, “Abstraction of continuous system to discrete event system using
neural network,” in AeroSense’97, 1997, pp. 42–51.
A. I. Concepcion and B. F. Zeigler, “DEVS formalism: A framework for hierarchical model
development,” IEEE Trans. Softw. Eng., vol. 14, no. 2, pp. 228–241, 1988.
S. J. Choi and T. G. Kim, “Identification of discrete event systems using the compound
recurrent neural network: Extracting DEVS from trained network,” Simulation, vol. 78, no.
2, pp. 90–104, 2002.
J. Filippi, P. Bisgambiglia, and M. Delhom, “Neuro-devs, an hybrid methodology to
describe complex systems,” in Proceedings of the SCS ESS 2002 conference on simulation
in industry, 2002, vol. 1, p. 647.
O. Gérard, Je.-N. Patillon, and F. D’Alché-Buc, “Discharge prediction of rechargeable
batteries with neural networks,” Integr. Comput.-Aided Eng., vol. 6, no. 1, pp. 41–52, 1999.
StudentsandScholarship Team.