Learning to recognize visual stimuli in neuromorphic VLSI

Federico Corradi; Massimiliano Giulioni

doi:10.1109/BioCAS.2012.6418494

Learning to recognize visual stimuli in neuromorphic VLSI

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

We demonstrate learning in a neuromorphic recurrent attractor network distributed onto two VLSI chips. On a monitor we present some stimuli which are input to the network through the neuromorphic retina. Stimulation induces modification in the synaptic weights up to the point in which the selective reverberant states of activity are supported in the absence of stimulus. The network activity and the evolution of the synaptic matrix are monitored during learning. The visitor can draw his/her own stimuli, he/she can modify the learning parameters to teach the network to recognize them.

Original language	English
Title of host publication	2012 IEEE Biomedical Circuits and Systems Conference (BioCAS)
Publisher	Institute of Electrical and Electronics Engineers
Pages	90-90
Number of pages	1
ISBN (Electronic)	978-1-4673-2293-5
DOIs	https://doi.org/10.1109/BioCAS.2012.6418494
Publication status	Published - 24 Jan 2013
Externally published	Yes
Event	2012 IEEE Biomedical Circuits and Systems Conference, BioCAS 2012 - Hsinchu, Taiwan, Zhubei, Taiwan Duration: 28 Nov 2012 → 30 Nov 2012 https://ieee-cas.org/conference/2012-ieee-biomedical-circuits-and-systems-conference-biocas

Conference

Conference	2012 IEEE Biomedical Circuits and Systems Conference, BioCAS 2012
Abbreviated title	BioCAS 2012
Country/Territory	Taiwan
City	Zhubei
Period	28/11/12 → 30/11/12
Other	2012 BIOCAS Biomedical Circuits and Systems Conference
Internet address	https://ieee-cas.org/conference/2012-ieee-biomedical-circuits-and-systems-conference-biocas

Keywords

Neuromorphics
Neurons
Visualization
Monitoring
Retina
Plastics

Access to Document

10.1109/BioCAS.2012.6418494

Cite this

@inproceedings{66cb91a52df747bb93ee28ec24afffba,

title = "Learning to recognize visual stimuli in neuromorphic VLSI",

abstract = "We demonstrate learning in a neuromorphic recurrent attractor network distributed onto two VLSI chips. On a monitor we present some stimuli which are input to the network through the neuromorphic retina. Stimulation induces modification in the synaptic weights up to the point in which the selective reverberant states of activity are supported in the absence of stimulus. The network activity and the evolution of the synaptic matrix are monitored during learning. The visitor can draw his/her own stimuli, he/she can modify the learning parameters to teach the network to recognize them.",

keywords = "Neuromorphics, Neurons, Visualization, Monitoring, Retina, Plastics",

author = "Federico Corradi and Massimiliano Giulioni",

year = "2013",

month = jan,

day = "24",

doi = "10.1109/BioCAS.2012.6418494",

language = "English",

pages = "90--90",

booktitle = "2012 IEEE Biomedical Circuits and Systems Conference (BioCAS)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2012 IEEE Biomedical Circuits and Systems Conference, BioCAS 2012, BioCAS 2012 ; Conference date: 28-11-2012 Through 30-11-2012",

url = "https://ieee-cas.org/conference/2012-ieee-biomedical-circuits-and-systems-conference-biocas",

}

TY - GEN

T1 - Learning to recognize visual stimuli in neuromorphic VLSI

AU - Corradi, Federico

AU - Giulioni, Massimiliano

PY - 2013/1/24

Y1 - 2013/1/24

N2 - We demonstrate learning in a neuromorphic recurrent attractor network distributed onto two VLSI chips. On a monitor we present some stimuli which are input to the network through the neuromorphic retina. Stimulation induces modification in the synaptic weights up to the point in which the selective reverberant states of activity are supported in the absence of stimulus. The network activity and the evolution of the synaptic matrix are monitored during learning. The visitor can draw his/her own stimuli, he/she can modify the learning parameters to teach the network to recognize them.

AB - We demonstrate learning in a neuromorphic recurrent attractor network distributed onto two VLSI chips. On a monitor we present some stimuli which are input to the network through the neuromorphic retina. Stimulation induces modification in the synaptic weights up to the point in which the selective reverberant states of activity are supported in the absence of stimulus. The network activity and the evolution of the synaptic matrix are monitored during learning. The visitor can draw his/her own stimuli, he/she can modify the learning parameters to teach the network to recognize them.

KW - Neuromorphics

KW - Neurons

KW - Visualization

KW - Monitoring

KW - Retina

KW - Plastics

U2 - 10.1109/BioCAS.2012.6418494

DO - 10.1109/BioCAS.2012.6418494

M3 - Conference contribution

SP - 90

EP - 90

BT - 2012 IEEE Biomedical Circuits and Systems Conference (BioCAS)

PB - Institute of Electrical and Electronics Engineers

T2 - 2012 IEEE Biomedical Circuits and Systems Conference, BioCAS 2012

Y2 - 28 November 2012 through 30 November 2012

ER -

Learning to recognize visual stimuli in neuromorphic VLSI

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this