Evolutionary multitasking : a computer science view of cognitive multitasking
The human mind possesses the most remarkable ability to perform multiple tasks with apparent simultaneity. In fact, with the present-day explosion in the variety and volume of incoming information streams that must be absorbed and appropriately processed, the opportunity, tendency, and (even) the ne...
Saved in:
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/147973 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-147973 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1479732021-04-16T01:58:09Z Evolutionary multitasking : a computer science view of cognitive multitasking Ong, Yew-Soon Gupta, Abhishek School of Computer Science and Engineering Engineering::Computer science and engineering Multitask Optimization Evolutionary Multitasking The human mind possesses the most remarkable ability to perform multiple tasks with apparent simultaneity. In fact, with the present-day explosion in the variety and volume of incoming information streams that must be absorbed and appropriately processed, the opportunity, tendency, and (even) the need to multitask are unprecedented. Thus, it comes as little surprise that the pursuit of intelligent systems and algorithms that are capable of efficient multitasking is rapidly gaining importance among contemporary scientists who are faced with the increasing complexity of real-world problems. To this end, the present paper is dedicated to a detailed exposition on a so-far underexplored characteristic of population-based search algorithms, i.e., their inherent ability (much like the human mind) to handle multiple optimization tasks at once. We present a simple evolutionary methodology capable of cross-domainmultitask optimization in a unified genotype space and show that there exist many potential benefits of its application in practical domains. Most notably, it is revealed that multitasking enables one to automatically leverage upon the underlying commonalities between distinct optimization tasks, thereby providing the scope for considerably improved performance in real-world problem solving. Accepted version 2021-04-16T01:58:09Z 2021-04-16T01:58:09Z 2016 Journal Article Ong, Y. & Gupta, A. (2016). Evolutionary multitasking : a computer science view of cognitive multitasking. Cognitive Computation, 8(2), 125-142. https://dx.doi.org/10.1007/s12559-016-9395-7 1866-9956 https://hdl.handle.net/10356/147973 10.1007/s12559-016-9395-7 2-s2.0-84960334037 2 8 125 142 en Cognitive Computation © 2016 Springer Science+Business Media. This is a post-peer-review, pre-copyedit version of an article published in Cognitive Computation. The final authenticated version is available online at: http://dx.doi.org/10.1007/s12559-016-9395-7. application/pdf |
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 Multitask Optimization Evolutionary Multitasking |
spellingShingle |
Engineering::Computer science and engineering Multitask Optimization Evolutionary Multitasking Ong, Yew-Soon Gupta, Abhishek Evolutionary multitasking : a computer science view of cognitive multitasking |
description |
The human mind possesses the most remarkable ability to perform multiple tasks with apparent simultaneity. In fact, with the present-day explosion in the variety and volume of incoming information streams that must be absorbed and appropriately processed, the opportunity, tendency, and (even) the need to multitask are unprecedented. Thus, it comes as little surprise that the pursuit of intelligent systems and algorithms that are capable of efficient multitasking is rapidly gaining importance among contemporary scientists who are faced with the increasing complexity of real-world problems. To this end, the present paper is dedicated to a detailed exposition on a so-far underexplored characteristic of population-based search algorithms, i.e., their inherent ability (much like the human mind) to handle multiple optimization tasks at once. We present a simple evolutionary methodology capable of cross-domainmultitask optimization in a unified genotype space and show that there exist many potential benefits of its application in practical domains. Most notably, it is revealed that multitasking enables one to automatically leverage upon the underlying commonalities between distinct optimization tasks, thereby providing the scope for considerably improved performance in real-world problem solving. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Ong, Yew-Soon Gupta, Abhishek |
format |
Article |
author |
Ong, Yew-Soon Gupta, Abhishek |
author_sort |
Ong, Yew-Soon |
title |
Evolutionary multitasking : a computer science view of cognitive multitasking |
title_short |
Evolutionary multitasking : a computer science view of cognitive multitasking |
title_full |
Evolutionary multitasking : a computer science view of cognitive multitasking |
title_fullStr |
Evolutionary multitasking : a computer science view of cognitive multitasking |
title_full_unstemmed |
Evolutionary multitasking : a computer science view of cognitive multitasking |
title_sort |
evolutionary multitasking : a computer science view of cognitive multitasking |
publishDate |
2021 |
url |
https://hdl.handle.net/10356/147973 |
_version_ |
1698713738574561280 |