Cascade complex systems — Global modeling using neural networks

2016 ◽  
Author(s):  
Grzegorz Dralus ◽  
Damian Mazur
Keyword(s):  
Neural Networks ◽  
Complex Systems ◽  
Global Modeling ◽  
Cascade Complex

Modularity in Artificial Neural Networks

2011 ◽  
pp. 1095-1101
Author(s):  
Ricardo Téllez ◽  
Cecilio Angulo
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Complex Systems ◽  
Intelligent Systems ◽  
Point Of View ◽  
Main Concern ◽  
Complex Structures ◽  
Computational Point ◽  
Points Of View

The concept of modularity is a main concern for the generation of artificially intelligent systems. Modularity is an ubiquitous organization principle found everywhere in natural and artificial complex systems (Callebaut, 2005). Evidences from biological and philosophical points of view (Caelli and Wen, 1999) (Fodor, 1983), indicate that modularity is a requisite for complex intelligent behaviour. Besides, from an engineering point of view, modularity seems to be the only way for the construction of complex structures. Hence, whether complex neural programs for complex agents are desired, modularity is required. This article introduces the concepts of modularity and module from a computational point of view, and how they apply to the generation of neural programs based on modules. Two levels, strategic and tactical, at which modularity can be implemented, are identified. How they work and how they can be combined for the generation of a completely modular controller for a neural network based agent is presented.

scholarly journals Recurrent Trainable Neural Networks for Complex Systems Identification: A Hybrid System Approach

2016 ◽  
Vol 118 (1) ◽  
pp. 97-106
Author(s):  
Juan-Eduardo Velázquez-Velázquez ◽  
Rosalba Galván-Guerra ◽  
Ieroham Baruch ◽  
Silvestre Garcia-Sanchez
Keyword(s):  
Neural Networks ◽  
Complex Systems ◽  
Hybrid System ◽  
System Approach ◽  
Systems Identification

scholarly journals TOWARDS EVOLUTIONARY DESIGN OF COMPLEX SYSTEMS INSPIRED BY NATURE

2014 ◽  
Vol 54 (5) ◽  
pp. 367-377
Author(s):  
Jaroslav Vítku ◽  
Pavel Nahodil
Keyword(s):  
Neural Networks ◽  
Complex Systems ◽  
Human Brain ◽  
Evolutionary Algorithm ◽  
Autonomous Systems ◽  
Hybrid Networks ◽  
Evolutionary Design ◽  
Agent Architecture ◽  
Simple Experiment ◽  
Agent Architectures

This paper presents first steps towards evolutionary design of complex autonomous systems. The approach is inspired in modularity of human brain and principles of evolution. Rather than evolving neural networks or neural-based systems, the approach focuses on evolving hybrid networks composed of heterogeneous sub-systems implementing various algorithms/behaviors. Currently, the evolutionary techniques are used to optimize weights between predefined blocks (so called Neural Modules) in order to find an agent architecture appropriate for given task. The framework, together with the simulator of such systems is presented. Then, examples of agent architectures represented as hybrid networks are presented. One architecture is hand-designed and one is automatically optimized by means of evolutionary algorithm. Even on such a simple experiment, it can be observed how the evolution is able to pick-up unexpected attributes of the task and exploit them when designing new architecture.

scholarly journals A Novel Technique for Solving Fully Fuzzy Nonlinear Systems Based on Neural Networks

2020 ◽  
Vol 07 (01) ◽  
pp. 93-107 ◽  
Author(s):  
Raheleh Jafari ◽  
Sina Razvarz ◽  
Alexander Gegov
Keyword(s):  
Neural Networks ◽  
Nonlinear System ◽  
Nonlinear Systems ◽  
Complex Systems ◽  
Gradient Descent ◽  
Descent Algorithm ◽  
Novel Technique ◽  
New Approaches ◽  
Gradient Descent Algorithm

Predicting the solutions of complex systems is a crucial challenge. Complexity exists because of the uncertainty as well as nonlinearity. The nonlinearity in complex systems makes uncertainty irreducible in several cases. In this paper, two new approaches based on neural networks are proposed in order to find the estimated solutions of the fully fuzzy nonlinear system (FFNS). For obtaining the estimated solutions, a gradient descent algorithm is proposed in order to train the proposed networks. An example is proposed in order to show the efficiency of the considered approaches.

COMPLEXITY: METRICS AND MODULES

2003 ◽  
Vol 06 (03) ◽  
pp. 313-329 ◽  
Author(s):  
TERRY BOSSOMAIER
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Cellular Automata ◽  
Complex Systems ◽  
Cognitive Processing ◽  
Communication Protocols ◽  
Emergent Behavior ◽  
Modular Construction ◽  
System Complexity ◽  
Complexity Metrics

Complex systems are of vast importance in the practical world as well as presenting many theoretical challenges. The measurement of system complexity is still imprecise. For many systems, their modular construction brings challenges in understanding how modules form and the emergent behavior which may result. In other systems, it is the development of encodings and communication protocols which allow complexity to increase dramatically. We take a broad view of these issues and then consider the nature of the system space which generates complexity. We show examples from cellular automata and applications of neural networks to data mining which suggest that complex systems often occupy simple structured sub-spaces. Finally, we look at the way modularity relates to networks and the implications for understanding human cognitive processing.

Sign in / Sign up

Export Citation Format

Share Document