@article{oai:kyutech.repo.nii.ac.jp:00007479,
 author = {Ikemoto, Shuhei and 池本, 周平 and Takahara,  Kazuma and Kumi,  Taiki and Hosoda,  Koh},
 journal = {SN Computer Science},
 month = {Jan},
 note = {Neural networks have been widely used to model nonlinear systems that are difficult to formulate. Thus far, because neural networks are a radically different approach to mathematical modeling, control theory has not been applied to them, even if they approximate the nonlinear state equation of a control object. In this research, we propose a new approach—i.e., neural model extraction, that enables model-based control for a feed-forward neural network trained for a nonlinear state equation. Specifically, we propose a method for extracting the linear state equations that are equivalent to the neural network corresponding to given input vectors. We conducted simple simulations of a two degrees-of-freedom planar manipulator to verify how the proposed method enables model-based control on neural network forward models. Through simulations, where different settings of the manipulator’s state observation are assumed, we successfully confirm the validity of the proposed method.},
 pages = {54-1--54-14},
 title = {Neural Model Extraction for Model-Based Control of a Neural Network Forward Model},
 volume = {2},
 year = {2021},
 yomi = {イケモト, シュウヘイ}
}