Pasemann F & Dieckmann U (1997). Evolved neurocontrollers for pole balancing. In: Biological and Artificial Computation: From Neuroscience to Technology - Proceedings of IWANN '97, 4-6 June 1997.Full text not available from this repository.
An evolutionary algorithm for the development of neural networks with arbitrary connectivity is presented. The algorithm is not based on genetic Mgorithms, but is inspired by a biological theory of coevolving species. It sets no constraints on the number of neurons and the architecture of a network, and develops network topology and parameters like weights and bias terms simultaneously. Designed for generating neuromodules acting in embedded systems like autonomous agents, it can be used also for the evolution of neural networks solving nonlinear control problems. Here we report on a first test, where the algorithm is applied to a standard control problem: The balancing of an inverted pendulum.
|Item Type:||Conference or Workshop Item (UNSPECIFIED)|
|Uncontrolled Keywords:||Algorithms; Autonomous agents; Bioinformatics; Biology; Electric network topology; Control problems; Inverted pendulum; Network topology; Neuro controllers; Nonlinear control problems|
|Research Programs:||Adaptive Dynamics Network (ADN)|
|Bibliographic Reference:||In: J. Mira, R. Moreno-Diaz, J. Cabestany (eds); Biological and Artificial Computation: From Neuroscience to Technology - Proceedings of IWANN '97; 4-6 June 1997, Lanzarote, Spain|
|Depositing User:||IIASA Import|
|Date Deposited:||15 Jan 2016 02:08|
|Last Modified:||20 Jan 2016 16:41|
Actions (login required)