Spiking neural network for object recognition

While artificial intelligence technology has made significant strides and found wideranging applications, there persists a demand for a more intricately designed AI system that emulates natural intelligence. One promising avenue is the utilization of Spiking Neural Networks (SNNs), constructed fr...

Full description

Saved in:
Bibliographic Details
Main Author: Li, Wei
Other Authors: Meng-Hiot Lim
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/172518
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-172518
record_format dspace
spelling sg-ntu-dr.10356-1725182023-12-15T15:45:14Z Spiking neural network for object recognition Li, Wei Meng-Hiot Lim School of Electrical and Electronic Engineering EMHLIM@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence While artificial intelligence technology has made significant strides and found wideranging applications, there persists a demand for a more intricately designed AI system that emulates natural intelligence. One promising avenue is the utilization of Spiking Neural Networks (SNNs), constructed from spiking neurons to replicate the biologically plausible computations observed in the brain. Unlike most other networks that operate on a time-based paradigm, SNNs employ event-driven methodologies, and researchers have extensively investigated their performance. This dissertation centers on the application of SNNs in the domain of object recognition. It evaluates the performance of the Spatio-Temporal Backpropagation (STBP) method within a shallow network architecture on benchmark datasets including MNIST, CIFAR-10, and CIFAR-100 for image classification, comparing it with traditional Convolutional Neural Networks (CNNs). The method of batch normalization through time was employed to optimize the training process. Additionally, a deeper neural network was utilized to analyze the performance of the SNN, with the aim of improving phoneme recognition. Ultimately, this work culminates in a comprehensive review of recent advancements in SNNs, providing valuable insights into the current state of the field. Master of Science (Signal Processing) 2023-12-13T07:44:26Z 2023-12-13T07:44:26Z 2023 Thesis-Master by Coursework Li, W. (2023). Spiking neural network for object recognition. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/172518 https://hdl.handle.net/10356/172518 en ISM-DISS-02812 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
spellingShingle Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Li, Wei
Spiking neural network for object recognition
description While artificial intelligence technology has made significant strides and found wideranging applications, there persists a demand for a more intricately designed AI system that emulates natural intelligence. One promising avenue is the utilization of Spiking Neural Networks (SNNs), constructed from spiking neurons to replicate the biologically plausible computations observed in the brain. Unlike most other networks that operate on a time-based paradigm, SNNs employ event-driven methodologies, and researchers have extensively investigated their performance. This dissertation centers on the application of SNNs in the domain of object recognition. It evaluates the performance of the Spatio-Temporal Backpropagation (STBP) method within a shallow network architecture on benchmark datasets including MNIST, CIFAR-10, and CIFAR-100 for image classification, comparing it with traditional Convolutional Neural Networks (CNNs). The method of batch normalization through time was employed to optimize the training process. Additionally, a deeper neural network was utilized to analyze the performance of the SNN, with the aim of improving phoneme recognition. Ultimately, this work culminates in a comprehensive review of recent advancements in SNNs, providing valuable insights into the current state of the field.
author2 Meng-Hiot Lim
author_facet Meng-Hiot Lim
Li, Wei
format Thesis-Master by Coursework
author Li, Wei
author_sort Li, Wei
title Spiking neural network for object recognition
title_short Spiking neural network for object recognition
title_full Spiking neural network for object recognition
title_fullStr Spiking neural network for object recognition
title_full_unstemmed Spiking neural network for object recognition
title_sort spiking neural network for object recognition
publisher Nanyang Technological University
publishDate 2023
url https://hdl.handle.net/10356/172518
_version_ 1787136486107250688