Multi-criteria Evolution of Neural Network Topologies: Balancing Experience and Performance in Autonomous Systems
This work addresses the challenge of improving generalization and reducing overfitting in autonomous systems, particularly for small-robot path-planning, though it is incremental as it builds upon the existing NEAT paradigm.
The paper tackles the problem of sub-optimal performance and low portability in autonomous systems due to fixed neural network topologies by developing a multi-objective neuro-evolution algorithm that balances performance and experience-gain, resulting in superior performance in unseen scenarios for small-robot path-planning applications.
Majority of Artificial Neural Network (ANN) implementations in autonomous systems use a fixed/user-prescribed network topology, leading to sub-optimal performance and low portability. The existing neuro-evolution of augmenting topology or NEAT paradigm offers a powerful alternative by allowing the network topology and the connection weights to be simultaneously optimized through an evolutionary process. However, most NEAT implementations allow the consideration of only a single objective. There also persists the question of how to tractably introduce topological diversification that mitigates overfitting to training scenarios. To address these gaps, this paper develops a multi-objective neuro-evolution algorithm. While adopting the basic elements of NEAT, important modifications are made to the selection, speciation, and mutation processes. With the backdrop of small-robot path-planning applications, an experience-gain criterion is derived to encapsulate the amount of diverse local environment encountered by the system. This criterion facilitates the evolution of genes that support exploration, thereby seeking to generalize from a smaller set of mission scenarios than possible with performance maximization alone. The effectiveness of the single-objective (optimizing performance) and the multi-objective (optimizing performance and experience-gain) neuro-evolution approaches are evaluated on two different small-robot cases, with ANNs obtained by the multi-objective optimization observed to provide superior performance in unseen scenarios.