Co-evolutionary modular neural networks for automatic problem decomposition

Abstract- Decomposing a complex computational problem into sub-problems, which are computationally simpler to solve individually and which can be combined to produce a solution to the full problem, can efficiently lead to compact and general solutions. Modular neural networks represent one of the ways in which this divide-and-conquer strategy can be implemented. Here we present a co-evolutionary model which is used to design and optimize modular neural networks with taskspecific modules. The model consists of two populations. The first population consists of a pool of modules and the second population synthesizes complete systems by drawing elements from the pool of modules. Modules represent a part of the solution, which co-operates with others in the module population to form a complete solution. With the help of two artificial supervised learning tasks created by mixing two sub-tasks we demonstrate that if a particular task decomposition is better in terms of performance on the ...

• Type: Conference
• Year: 2005
• Where: CEC
• Authors: Vineet R. Khare, Xin Yao, Bernhard Sendhoff, Yaochu Jin, Heiko Wersing
• Keywords: Artificial Intelligence, CEC 2005, Co-evolutionary Model, Complex Computational Problem, Modular Neural Networks