Powering Next-Generation Artificial Intelligence by Designing Three-dimensional High-Performance Neuromorphic Computing System with Memristors

Simple item page
dc.contributor.authorAn, Hongyuen
dc.contributor.committeechairYi, Yangen
dc.contributor.committeememberHa, Dong S.en
dc.contributor.committeememberKurdila, Andrew J.en
dc.contributor.committeememberLiu, Lingjiaen
dc.contributor.committeememberZhou, Zhenen
dc.contributor.committeememberOrlowski, Mariusz Kriysztofen
dc.contributor.departmentElectrical Engineeringen
dc.date.accessioned2021-01-12T07:00:21Zen
dc.date.available2021-01-12T07:00:21Zen
dc.date.issued2020-09-17en
dc.description.abstractHuman brains can complete numerous intelligent tasks, such as pattern recognition, reasoning, control and movement, with remarkable energy efficiency (20 W). In contrast, a typical computer only recognizes 1,000 different objects but consumes about 250 W power [1]. This performance significant differences stem from the intrinsic different structures of human brains and digital computers. The latest discoveries in neuroscience indicate the capabilities of human brains are attributed to three unique features: (1) neural network structure; (2) spike-based signal representation; (3) synaptic plasticity and associative memory learning [1, 2]. In this dissertation, the next-generation platform of artificial intelligence is explored by utilizing memristors to design a three-dimensional high-performance neuromorphic computing system. The low-variation memristors (fabricated by Virginia Tech) reduce the learning accuracy of the system significantly through adding heat dissipation layers. Moreover, three emerging neuromorphic architectures are proposed showing a path to realizing the next-generation platform of artificial intelligence with self-learning capability and high energy efficiency. At last, an Associative Memory Learning System is exhibited to reproduce an associative memory learning that remembers and correlates two concurrent events (pronunciation and shape of digits) together.en
dc.description.abstractgeneralIn this dissertation, the next-generation platform of artificial intelligence is explored by utilizing memristors to design a three-dimensional high-performance neuromorphic computing system. The low-variation memristors (fabricated by Virginia Tech) reduce the learning accuracy of the system significantly through adding heat dissipation layers. Moreover, three emerging neuromorphic architectures are proposed showing a path to realizing the next-generation platform of artificial intelligence with self-learning capability and high energy efficiency. At last, an Associative Memory Learning System is exhibited to reproduce an associative memory learning that remembers and correlates two concurrent events (pronunciation and shape of digits) together.en
dc.description.degreeDoctor of Philosophyen
dc.format.mediumETDen
dc.identifier.othervt_gsexam:27163en
dc.identifier.urihttp://hdl.handle.net/10919/101838en
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectMemristorsen
dc.subjectNeuromorphic Computingen
dc.subjectArtificial Intelligenceen
dc.titlePowering Next-Generation Artificial Intelligence by Designing Three-dimensional High-Performance Neuromorphic Computing System with Memristorsen
dc.typeDissertationen
thesis.degree.disciplineElectrical Engineeringen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.leveldoctoralen
thesis.degree.nameDoctor of Philosophyen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
An_H_D_2020.pdf
Size:
5.14 MB
Format:
Adobe Portable Document Format
Download

Collections

Doctoral Dissertations