LEARNING TO TEACH TO NEURAL NETWORKS HOW TO LEARN WELL WITH SOH, A SELF-OBSERVING HEURISTIC

In this ongoing research, we present a Self-Observing Heuristic (SOH). SOH is a hybrid computing method. It roots in natural selection and optimization techniques to provide an environmentally driven evolutionary computation scheme, capable of autonomic cumulative learning. Our aim is to realize an adaptive learning system based on neo- Darwinian evolution of neural units. We proceed in two complementary directions. On one hand, we try to automati- cally compute the costly tuning phase of the configuration and learning parameters of neural networks (NNs). On the other hand, we use meiosis cellular growth as a natural computation technique to bypass palimpsest effects observed when adding new knowledge to previous one. The main idea is to build an event guided growing competitive NN that develops while it learns to tune other NNs' parameters. Other NNs can be models more or less similar - or even iden- tical - to it. The system adapts itself, learning to teach other models how to learn well.