A reconfigurable spiking neural network is implemented in a 0.5µm CMOS digital tiny-chip. The connection weights are uploaded to registers on the ASIC. These weights are learned off-line, using combined simulated annealing and genetic algorithm. Large computational power and many simulations create small powerful networks that are adapted to interact with the environment. These configurations are swapped in and out of the ASIC to cope with varying situations and increase robustness. The network has been successfully tested with a simulated robot in a maze and can be extended for target recognition.
A reconfigurable spiking neural network digital ASIC simulation and implementation
2009-07-01
1540198 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Neuromorphic Implementation of Spiking Relational Neural Network for Motor Control
BASE | 2020
|Small Microprocessor for ASIC or FPGA Implementation
Online Contents | 2011
Differential mapping spiking neural network for sensor-based robot control
BASE | 2021
|An ASIC Digital Video Processing Library
British Library Online Contents | 1991
|Unterhaltungselektronik: ASIC fur Digital Radio Mondial
British Library Online Contents | 2007