國立虎尾科技大學 |

Bio-Inspired Memory Device Based Physical Reservoir Computing System to Solve Temporal and Classification Problems.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Bio-Inspired Memory Device Based Physical Reservoir Computing System to Solve Temporal and Classification Problems./
Author:	Hossain, Md. Razuan.
Description:	1 online resource (146 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
Contained By:	Dissertations Abstracts International85-04B.
Subject:	Computer engineering. -
Online resource:	click for full text (PQDT)
ISBN:	9798380577854

Bio-Inspired Memory Device Based Physical Reservoir Computing System to Solve Temporal and Classification Problems.
Hossain, Md. Razuan.

Bio-Inspired Memory Device Based Physical Reservoir Computing System to Solve Temporal and Classification Problems. - 1 online resource (146 pages)

Source: Dissertations Abstracts International, Volume: 85-04, Section: B.

Thesis (Ph.D.)--The University of Mississippi, 2023.

Includes bibliographical references

In recent years, technological advancements in the field of computing have been limited by the slowing down of Moore's law, which predicts the doubling of the number of transistors on a microchip every two years. The limitations of traditional solid-state electronics have become increasingly evident, as it is becoming difficult to increase the number of transistors while maintaining their reliability and performance. The breakdown of Dennard Scaling, which describes the power-density relationship in CMOS transistors, and the von Neumann bottleneck, which refers to the limited bandwidth between the central processing unit (CPU) and memory, have further exacerbated the situation. Moreover, the ever-increasing computing demands have led researchers to explore alternative computing mechanisms, such as neuromorphic computing.In this context, there is a growing interest in developing novel memory devices that possess non-linear current-voltage characteristics and inherent memory properties, such as bio-inspired memory devices. These devices are inspired by the functioning of biological synapses in the brain, which enable neurons to communicate with each other and form complex networks. Bio-mem devices use biomolecules, such as proteins or DNA, as their active material and can exhibit a range of non-linear behaviors, including hysteresis, threshold switching, and negative differential resistance. Additionally, they have inherent memory properties that allow them to retain their state even after the power is turned off. The unique features of bio-mem devices make them a promising candidate for solving classification and temporal pattern recognition tasks. Unlike their solid-state counter-parts, bio-mem devices feature a similar structure, switching mechanism, and ionic transport modality as biological synapses, while consuming considerably lower power. The use of bio-mem devices in computing can lead to the development of more efficient and powerful computing systems that can handle complex tasks more effectively. One promising computing paradigm that has emerged in recent years is Reservoir Computing (RC), which is a type of recurrent neural network that uses a fixed, random, and sparse connectivity matrix called a "reservoir." The reservoir provides a non-linear mapping of the input data, and the output is obtained by training a linear readout layer using a simple learning algorithm, such as ridge regression or support vector regression. RC has been shown to be effective in solving a range of classification and temporal problems, such as speech recognition, time-series prediction, and image classification. This work aims to explore the use of biomolecular devices in RC to solve classification and temporal problems, which could lead to the development of more efficient and powerful computing systems.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380577854Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

Central processing unitIndex Terms--Genre/Form:

554714
Electronic books.

Bio-Inspired Memory Device Based Physical Reservoir Computing System to Solve Temporal and Classification Problems.
LDR:04309ntm a22003977 4500 001 1141769
005 20240414211513.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380577854
035 $a (MiAaPQ)AAI30575576
035 $a AAI30575576
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Hossain, Md. Razuan. $3 1465735
245 1 0 $a Bio-Inspired Memory Device Based Physical Reservoir Computing System to Solve Temporal and Classification Problems.
264 0 $c 2023
300 $a 1 online resource (146 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
500 $a Advisor: Viswanathan, Ramanarayanan;Hasan, Md Sakib.
502 $a Thesis (Ph.D.)--The University of Mississippi, 2023.
504 $a Includes bibliographical references
520 $a In recent years, technological advancements in the field of computing have been limited by the slowing down of Moore's law, which predicts the doubling of the number of transistors on a microchip every two years. The limitations of traditional solid-state electronics have become increasingly evident, as it is becoming difficult to increase the number of transistors while maintaining their reliability and performance. The breakdown of Dennard Scaling, which describes the power-density relationship in CMOS transistors, and the von Neumann bottleneck, which refers to the limited bandwidth between the central processing unit (CPU) and memory, have further exacerbated the situation. Moreover, the ever-increasing computing demands have led researchers to explore alternative computing mechanisms, such as neuromorphic computing.In this context, there is a growing interest in developing novel memory devices that possess non-linear current-voltage characteristics and inherent memory properties, such as bio-inspired memory devices. These devices are inspired by the functioning of biological synapses in the brain, which enable neurons to communicate with each other and form complex networks. Bio-mem devices use biomolecules, such as proteins or DNA, as their active material and can exhibit a range of non-linear behaviors, including hysteresis, threshold switching, and negative differential resistance. Additionally, they have inherent memory properties that allow them to retain their state even after the power is turned off. The unique features of bio-mem devices make them a promising candidate for solving classification and temporal pattern recognition tasks. Unlike their solid-state counter-parts, bio-mem devices feature a similar structure, switching mechanism, and ionic transport modality as biological synapses, while consuming considerably lower power. The use of bio-mem devices in computing can lead to the development of more efficient and powerful computing systems that can handle complex tasks more effectively. One promising computing paradigm that has emerged in recent years is Reservoir Computing (RC), which is a type of recurrent neural network that uses a fixed, random, and sparse connectivity matrix called a "reservoir." The reservoir provides a non-linear mapping of the input data, and the output is obtained by training a linear readout layer using a simple learning algorithm, such as ridge regression or support vector regression. RC has been shown to be effective in solving a range of classification and temporal problems, such as speech recognition, time-series prediction, and image classification. This work aims to explore the use of biomolecular devices in RC to solve classification and temporal problems, which could lead to the development of more efficient and powerful computing systems.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 569006
650 4 $a Bioinformatics. $3 583857
650 4 $a Electrical engineering. $3 596380
653 $a Central processing unit
653 $a Neuromorphic computing
653 $a Memory devices
653 $a Biological synapses
653 $a Computing systems
655 7 $a Electronic books. $2 local $3 554714
690 $a 0464
690 $a 0544
690 $a 0715
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The University of Mississippi. $b Engineering Science. $3 1465736
773 0 $t Dissertations Abstracts International $g 85-04B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30575576 $z click for full text (PQDT)