DOI: 10.1007/978-3-540-70829-2_2
|View full text |Cite
|
Sign up to set email alerts
|

Opposition-Based Computing

Abstract: Summary. Diverse forms of opposition are already existent virtually everywhere around us but the nature and significance of oppositeness is well understood only in specific contexts within the fields of philosophy, linguistics, psychology, logic and physics. The interplay between entities and opposite entities is apparently fundamental for maintaining universal balance. However, it seems that there is a gap regarding oppositional thinking in engineering, mathematics and computer science. Although many oppositi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
9
0
1

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 23 publications
(10 citation statements)
references
References 22 publications
0
9
0
1
Order By: Relevance
“…Morales (2004) shows how a relational representation can be used to produce powerful abstractions which can significantly reduced the search space, and that learning over this abstracted space can help us to re-use previously learned policies on new problems. Tizhoosh (Tizhoosh, 2005;Tizhoosh et al, 2008) presents opposition-based learning as a scheme for machine intelligence that estimates and counter-estimates, weights and opposite weights, and actions versus counteractions which are the foundation of this new approach. Shokri (Shokri et al, 2008;Shokri, 2011) proposes the concept of opposition for each action within reinforcement learning techniques to update the value function (the agent is given a penalty when an action is performed) in order to improve the performance of existing methods in terms of running time.…”
Section: Reinforcement Learningmentioning
confidence: 99%
“…Morales (2004) shows how a relational representation can be used to produce powerful abstractions which can significantly reduced the search space, and that learning over this abstracted space can help us to re-use previously learned policies on new problems. Tizhoosh (Tizhoosh, 2005;Tizhoosh et al, 2008) presents opposition-based learning as a scheme for machine intelligence that estimates and counter-estimates, weights and opposite weights, and actions versus counteractions which are the foundation of this new approach. Shokri (Shokri et al, 2008;Shokri, 2011) proposes the concept of opposition for each action within reinforcement learning techniques to update the value function (the agent is given a penalty when an action is performed) in order to improve the performance of existing methods in terms of running time.…”
Section: Reinforcement Learningmentioning
confidence: 99%
“…This is the standard approach for multiple-dimension opposition and treats each dimension independently [39]. Other approaches, such as type 2 opposition [40], could be used for multiple-dimension opposition, but we do not address such approaches in this paper.…”
Section: Opposition Probabilities In Higher Dimensionsmentioning
confidence: 99%
“…4. Since the opposition function is called twice, the EA is classified as an initializing and somatic explicit oppositionbased computing algorithm [40]. As the opposite population's fitness has to be evaluated, oppositional EA will have to converge faster than original EA (in terms of generation count) in order to maintain the same CPU load.…”
Section: Oppositional Evolutionary Optimizationmentioning
confidence: 99%
“…GA is one of the most popular EA and many variations of it exist in the literature [156]. We employ GA with uniform crossover and roulette-wheel selection as described in Algorithms 3, 4.…”
Section: Genetic Algorithmsmentioning
confidence: 99%