Forgetting memristor based neuromorphic system for pattern training and recognition Academic Article

abstract

• 2016 Elsevier B.V. This paper presents a neuromorphic system for mean variance based pattern training and recognition. The system contains a self-learning circuit, a training circuit and a recognition circuit. Memristor model with forgetting effect which has memory ability and forgetting effect simultaneously is applied to simulate forgetting mechanism of neuromorphic system. Different from previous work, which divided training circuit as off line process, here the weight-changing circuit and the recognition part are combined on line for pattern training and recognition. For illustration, the whole neuromorphic system is applied to recognize handwriting number 09 on gray images, and simulations verify its effectiveness.

authors

• Huang, Tingwen

published proceedings

• NEUROCOMPUTING

author list (cited authors)

• Zhang, P., Li, C., Huang, T., Chen, L., & Chen, Y.

citation count

• 25

complete list of authors

• Zhang, Peijian||Li, Chuandong||Huang, Tingwen||Chen, Ling||Chen, Yiran

publication date

• January 2017

publisher

• Elsevier  Publisher

published in

• Neurocomputing  Journal

keywords

• Crossbar
• Memristors
• Neuromorphic System
• Pattern Training And Recognition

Digital Object Identifier (DOI)

• 10.1016/j.neucom.2016.10.012

start page

• 47

end page

• 53

volume

• 222

URL

• http://dx.doi.org/10.1016/j.neucom.2016.10.012