Seeing the light: artificial evolution, real vision
SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
Incremental evolution of complex general behavior
Adaptive Behavior - Special issue on environment structure and behavior
Embedded neural networks: exploiting constraints
Neural Networks - Special issue on neural control and robotics: biology and technology
Localized versus distributed representations
The handbook of brain theory and neural networks
Evolving Neural Networks through Augmenting Topologies
Evolving Neural Networks through Augmenting Topologies
Emergence of Memory-Driven Command Neurons in Evolved Artificial Agents
Neural Computation
Evolution of homing navigation in a real mobile robot
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
IEEE Transactions on Neural Networks
Localization of function via lesion analysis
Neural Computation
High-dimensional analysis of evolutionary autonomous agents
Artificial Life
| Hi-index | 0.00 |
This paper presents the Functional Contribution Algorithm (FCA) that addresses the fundamental challenge of localizing functions in artificial and natural neural networks. The FCA is based on an assignment of contribution values to the elements of the network, such that the ability to predict the network's performance in response to multi-lesions is maximized. The algorithm is thoroughly examined on evolved neurocontrollers, which are simple enough, but not too simple. We demonstrate that the FCA portrays a stable set of contributions and accurate multi-lesion predictions, which are significantly better than those obtained based on the classical single-lesion approach. Our results demonstrate the potential of the FCA to provide insights into the organization of both animat and animate nervous systems.