|
|||
|---|---|---|---|
1. ThemeMemetic computation (MC) is a novel computational paradigm which incorporates the notion of “memes” as building blocks of knowledge for boosting the search performance of the artificial evolutionary systems. It has gained much attention and shown great success in a wide range of problems domains. For the last decades, the advantage of MC has been well established as an extension of the classical evolutionary algorithms, taking the form of hybrid, adaptative hybrid or memetic algorithms, where a meme is perceived as a form of individual learning procedure or local search operator in population-based search algorithms. In particular, most existing works have been manually crafted for problem solving in very specific domains. Nevertheless, falling back on the fundamental definition of a meme by Dawkins and Blackmore (i.e., as the fundamental building blocks of culture evolution), the potential merits or true nature of memes remains yet to be fully exploited. And current research of MC further culminates into a meme-centric “memetic automaton”. A memetic automaton is a software agent/optimizer made in emulation of a human being, that autonomously acquires increasing level of capability and intelligence through embedded memes learnt independently from the past experience, or via interactions with the others. In this place, the notion of meme is liberated free from the narrow scope of a local search/individual learning operator, and embody potentially diverse forms of problem-solving knowledge. For example, as the naturally building blocks of meaningful information, the recurring real-world patterns or structures (i.e., trees, graphs, artificial neural networks) of a problem domain can be viewed as forms of meme representation that infect agents’ perceptions, beliefs, minds, etc. Besides, unsupervised, supervised, reinforcement learning, etc, are potential tools that can facilitate learning pertaining to memes. Moreover, it is worth stressing that a major drawback of existing optimization approaches in the literature is the apparent lacking of automated knowledge transfers and reuse across problems. Memes in memetic automaton are naturally building blocks of meaningful information and supports reuse across problems. This capacity to draw on memes from past instances of problem-solving sessions thus allows the search to be more intelligent, leading to solutions that can be attained more efficiently on unseen problems of increasing complexity and dynamic in nature. Therefore, in this special issue, we aim to explore the current and ongoing research of the advanced meme-centric computation in computational intelligence. The focus is placed on the new manifestation, pattern generalization, adaptation, reusability and transferability of the advanced memetic computing, as exhibited by various meme-based and agent-based evolutionary systems, etc. 2. Scope of TopicsThe scope of this special issue covers, but is not limited to:
3. Important Dates
4. Guest EditorsDr. Yaqing Hou (houyq@dlut.edu.cn), School of computer science and engineering, Dalian University of Technology, China Dr. Yuan Yuan (yyuan@msu.edu), Department of Computer Science and Engineering, Michigan State University, USA Dr. Zexuan Zhu (zhuzx@szu.edu.cn), College of Computer Science and Software Engineering, Shenzhen University, China |
|||
