Abstract— This paper presents i-AA1 , a constructive, incremental learning algorithm for a special class of weightless, self-organizing networks. In i-AA1 , learning consists of ...
— In this paper, we study a qualitative property of a class of competitive learning (CL) models, which is called the multiplicatively biased competitive learning (MBCL) model, na...
Reinforcement learning induces non-stationarity at several levels. Adaptation to non-stationary environments is of course a desired feature of a fair RL algorithm. Yet, even if the...
Gradient-based numerical optimization of complex engineering designs offers the promise of rapidly producing better designs. However, such methods generally assume that the object...
This paper presents an approach to automatic discovery of functions in Genetic Programming. The approach is based on discovery of useful building blocks by analyzing the evolution...