Automatic programming of behavior-based robots using reinforcement learning
Artificial Intelligence
Constructive incremental learning from only local information
Neural Computation
MOSAIC Model for Sensorimotor Learning and Control
Neural Computation
Biological Cybernetics - Special Issue: Dynamic Principles
Incremental Leaning and Model Selection for Radial Basis Function Network through Sleep
IEICE - Transactions on Information and Systems
Hi-index | 0.00 |
This paper presents a new type of neural networks, a perturbational neural network to realize incremental learning in autonomous humanoid robots. In our previous work, a virtual learning system has been provided to realize exploring plausible behavior in a robot's brain. Neural networks can generate plausible behavior in unknown environment without time-consuming exploring. Although an autonomous robot should grow step by step, conventional neural networks forget prior learning by training with new dataset. Proposed neural networks features adding output in sub neural network to weights and thresholds in main neural network. Incremental learning and high generalization capability are realized by slightly changing a mapping of the main neural network. We showed that the proposed neural networks realize incremental learning without forgetting through numerical experiments with a two-dimensional stair-climbing bipedal robot.