In this paper, an insect brain-inspired computational structure was developed. The peculiarity of the core processing layer is the local connectivity among the spiking neurons, which allows for a representation under the cellular nonlinear network paradigm. Moreover, the processing layer works as a liquid state network with fixed internal connections and trainable output weights. Learning was accomplished by adopting a simple supervised, batch approach based on the calculation of the Moore–Penrose matrix. The architecture, taking inspiration from a specific neuropile of the insect brain, the mushroom bodies, is evaluated and compared with other standard and bio-inspired solutions present in the literature, referring to three different scenarios.
Titolo: | A CNN-based neuromorphic model for classification and decision control |
Autori interni: | |
Data di pubblicazione: | 2019 |
Rivista: | |
Handle: | http://hdl.handle.net/20.500.11769/364325 |
Appare nelle tipologie: | 1.1 Articolo in rivista |