Evolution of internal dynamics for neural network nodes

• Published in: Evolutionary intelligence 2009-03, Vol.1 (4), p.233-251
• Main Authors: Montana, David, VanWyk, Eric, Brinn, Marshall, Montana, Joshua, Milligan, Stephen
• Format: Article
• Language: English
• Subjects: Applications of Mathematics; Artificial Intelligence; Bioinformatics; Control; Engineering; Mathematical and Computational Engineering; Mechatronics; Research Paper; Robotics; Statistical Physics and Dynamical Systems
• ISSN: 1864-5909; 1864-5917
• DOI: 10.1007/s12065-009-0017-0

Most artificial neural networks have nodes that apply a simple static transfer function, such as a sigmoid or gaussian, to their accumulated inputs. This contrasts with biological neurons, whose transfer functions are dynamic and driven by a rich internal structure. Our artificial neural network approach, which we call state-enhanced neural networks , uses nodes with dynamic transfer functions based on n -dimensional real-valued internal state. This internal state provides the nodes with memory of past inputs and computations. The state update rules, which determine the internal dynamics of a node, are optimized by an evolutionary algorithm to fit a particular task and environment. We demonstrate the effectiveness of the approach in comparison to certain types of recurrent neural networks using a suite of partially observable Markov decision processes as test problems. These problems involve both sequence detection and simulated mice in mazes, and include four advanced benchmarks proposed by other researchers.