感性学習機能を備えたフレンドリーな形状デザインシステムの試作

概要

論文の詳細を見る
A user friendly shape design system which fits an users sense has been developed. The system has dials as operation devices. The dials can be defined by words which express users ideas. The system uses a neural network to convert users ideas which are input by the dials to geometric parameters. Using the neural network, relations between users ideas and geometric parameters can be defined while the relations are difficult to define mathematically or nonlinear. Learning data to define each words transformation function can be generated by an users selection of appropriate sets of source and destination shape samples for an idea expressed by the word. This learning procedure enables an user to make neural network parameters reflected the users sense. The system was evaluated by toy plane design experiments.
社団法人電気学会の論文