Particularity

2023/06/12 by Lee Spector, Li Ding, Spector, Lee +3 · 1 voice · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #I.2.2 #I.2.6 #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #cs.AI #cs.LG #cs.NE

paper · pdf · doi:10.48550/arxiv.2306.06812

Abstract

We describe a design principle for adaptive systems under which adaptation is driven by particular challenges that the environment poses, as opposed to average or otherwise aggregated measures of performance over many challenges. We trace the development of this "particularity" approach from the use of lexicase selection in genetic programming to "particularist" approaches to other forms of machine learning and to the design of adaptive systems more generally.

Cited by

• Vector Policy Optimization: Training for Diversity Improves Test-Time Search

Discussions

• So we should embrace the multi-dimensional nature of the world and the particularity of the challenges that it presents. arxiv.org/abs/2306.06812 [bsky, 2 points, 0 comments]

Related

• Fitness-based Adaptive Control of Parameters in Genetic Programming: Adaptive Value Setting of Mutation Rate and Flood Mechanisms
• Adaptation and Self-Organization in Evolutionary Algorithms
• Problem-solving benefits of down-sampled lexicase selection
• Building and Understanding Adaptive Systems: A Statistical/Numerical Approach to Factory Automation and Brain Research
• Adaptation to Unknown Situations as the Holy Grail of Learning-Based\n Self-Adaptive Systems: Research Directions