Touch Modality Classification using Spiking Neural Networks and Supervised-STDP Learning

被引：0

作者：

Dabbous, Ali ^{[1
,2
]}

Ibrahim, Ali ^{[1
]}

Valle, Maurizio ^{[1
]}

Bartolozzi, Chiara ^{[2
]}

机构：

[1] Univ Genoa, Connected Objects Sensing Mat Integrated Circuits, DITEN, Genoa, Italy

[2] Ist Italiano Tecnol IIT, Event Driven Percept Robot EDPR Lab, Genoa, Italy

来源：

2021 28TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS, AND SYSTEMS (IEEE ICECS 2021) | 2021年

关键词：

SNN; STDP; Touch Modality; LIF; tactile sensors;

D O I：

10.1109/ICECS53924.2021.9665453

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Spiking Neural Networks and synaptic learning have recently emerged as viable techniques to solve classification problems characterized by high computational efficiency when implemented on low-power neuromorphic hardware. This paper presents the implementation of a Spiking Neural Network endowed with supervised Spike Timing Dependent Plasticity for touch modality classification (e.g. poke, press, grab, squeeze, push, and rolling a wheel). Results demonstrates the ability of the network to learn appropriate connectivity patterns for the classification. The proposed network achieves a total accuracy of 88:3% overcoming similar state-of-the-art solutions.

引用

页数：4

共 50 条

[21] Evolutionary Spiking Neural Networks for Solving Supervised Classification Problems
Lopez-Vazquez, G.
Ornelas-Rodriguez, M.
Espinal, A.
Soria-Alcaraz, J. A.
Rojas-Dominguez, A.
Puga-Soberanes, H. J.
Carpio, J. M.
Rostro-Gonzalez, H.
[J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2019, 2019
[22] Interchangeable Hebbian and Anti-Hebbian STDP Applied to Supervised Learning in Spiking Neural Network
Chang, Che-Chia
Chen, Pin-Chun
Hudec, Boris
Liu, Po-Tsun
Hou, Tuo-Hung
[J]. 2018 IEEE INTERNATIONAL ELECTRON DEVICES MEETING (IEDM), 2018,
[23] Learning Pitch with STDP: A Computational Model of Place and Temporal Pitch Perception Using Spiking Neural Networks
Saeedi, Nafise Erfanian
Blamey, Peter J.
Burkitt, Anthony N.
Grayden, David B.
[J]. PLOS COMPUTATIONAL BIOLOGY, 2016, 12 (04)
[24] Semi-Supervised Learning Combining Backpropagation and STDP: STDP Enhances Learning by Backpropagation with a Small Amount of Labeled Data in a Spiking Neural Network
Furuya, Kotaro
Ohkubo, Jun
[J]. JOURNAL OF THE PHYSICAL SOCIETY OF JAPAN, 2021, 90 (07)
[25] Simplified spiking neural network architecture and STDP learning algorithm applied to image classification
Iakymchuk, Taras
Rosado-Munoz, Alfredo
Guerrero-Martinez, Juan F.
Bataller-Mompean, Manuel
Frances-Villora, Jose V.
[J]. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2015,
[26] Simplified spiking neural network architecture and STDP learning algorithm applied to image classification
Taras Iakymchuk
Alfredo Rosado-Muñoz
Juan F Guerrero-Martínez
Manuel Bataller-Mompeán
Jose V Francés-Víllora
[J]. EURASIP Journal on Image and Video Processing, 2015
[27] Memristive Spiking Neural Networks Trained with Unsupervised STDP
Zhou, Errui
Fang, Liang
Yang, Binbin
[J]. ELECTRONICS, 2018, 7 (12)
[28] Supervised Learning in Spiking Neural Networks with MLC PCM Synapses
Nandakumar, S. R.
Boybat, I.
Le Gallo, M.
Sebastian, A.
Rajendran, B.
Eleftheriou, E.
[J]. 2017 75TH ANNUAL DEVICE RESEARCH CONFERENCE (DRC), 2017,
[29] Supervised Learning Based on Temporal Coding in Spiking Neural Networks
Mostafa, Hesham
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (07) : 3227 - 3235
[30] Self-Supervised Contrastive Learning In Spiking Neural Networks
Bahariasl, Yeganeh
Kheradpisheh, Saeed Reza
[J]. PROCEEDINGS OF THE 13TH IRANIAN/3RD INTERNATIONAL MACHINE VISION AND IMAGE PROCESSING CONFERENCE, MVIP, 2024, : 181 - 185

← 1 2 3 4 5 →