Sign in
A trainable neuromorphic controller
Journal article

A trainable neuromorphic controller

Allon Guez and John Selinsky
Journal of robotic systems, Vol.5(4), pp.363-388
01 Aug 1988

Abstract

Neuromorphic architecture is employed in the design of Trainable Adaptive Controllers (TACs). A neurocontroller is designed for controlling a nonlinear dynamic system. Various training models are employed: linear, nonlinear,'human' and 'filtered human'. It is found that the computational features of neural networks offer useful capabilities, such as fast, real time, and robust performance when employed as trainable adaptive controllers. (Author)

Details

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

#11 Sustainable Cities and Communities

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Web of Science research areas
Robotics