An Artificial Neural Network Functionalized by Evolution
This addresses the challenge of optimizing network architectures for AI applications such as robotics and big-data, though it appears incremental as it builds on existing methods.
The paper tackles the problem of designing efficient neural network topologies by proposing a hybrid model that combines feed-forward neural networks with evolutionary mechanisms, resulting in the ability to find well-adapted topologies for tasks like control and pattern recognition, with early adaptation and structural convergence.
The topology of artificial neural networks has a significant effect on their performance. Characterizing efficient topology is a field of promising research in Artificial Intelligence. However, it is not a trivial task and it is mainly experimented on through convolutional neural networks. We propose a hybrid model which combines the tensor calculus of feed-forward neural networks with Pseudo-Darwinian mechanisms. This allows for finding topologies that are well adapted for elaboration of strategies, control problems or pattern recognition tasks. In particular, the model can provide adapted topologies at early evolutionary stages, and 'structural convergence', which can found applications in robotics, big-data and artificial life.