Machine learning, Self-organizing systems -- Design and construction, Artificial intelligence
"Learning Hardware" approach involves creating a computational network based on feedback from the environment (for instance, positive and negative examples from the trainer), and realizing this network in an array of Field Programmable Gate Arrays (FPGAs). Computational networks can be built based on incremental supervised learning (Neural Net training) or global construction (Decision Tree design). Here we advocate the approach to Learning Hardware based on Constructive Induction methods of Machine Learning (ML) using multivalued functions. This is contrasted with the Evolvable Hardware (EHW) approach in which learning/evolution is based on the genetic algorithm only.
Perkowski, Marek; Grygiel, Stanislaw; Chen, Qihong; and Mattson, Dave, "Constructive Induction Machines for Data Mining" (1999). Electrical and Computer Engineering Faculty Publications and Presentations. 179.