Hisaaki Hatano

The functional localization of neural networks using genetic algorithms

We presented an algorithm for extracting Boolean functions (propositions, rules) from the units in trained neural networks. The extracted Boolean functions make the hidden units understandable. However, in some cases, the extracted Boolean functions are complicated, and so are not understandable, which means that the hidden units are not functionally localized. This paper presents an algorithm for the functional localization of (the hidden units of) neural networks. When a hidden unit is well approximated to a low-order Boolean function, the unit can be regarded as functionally localized. The functional localization of a hidden unit is evaluated by the error between the hidden unit and the low-order Boolean function extracted from the hidden unit. The optimization is executed by genetic algorithms. We applied it to vote data, mushroom data and chess data. Experimental results show that the algorithm works well.

An optimal control system with data mining method for saving electricity

An energy conservation optimal control system using information network is presented in the paper. The special feature of the control system is to control total equipments in a factory for energy conservation at low cost using information networks. The control strategy consists of 2 parts. (1) Data mining algorithm to examine energy consumption for a factory. (2) Optimal control algorithm to control many manipulating values at the same time. The algorithm adopts model predictive control method. The system performance is tested through energy consumption simulations for the factory whose model is proved by the comparison with measured data for 1 month. Finally the system was proved to decrease energy consumption by more than 8% that is our final goal.