期刊簡(jiǎn)介預(yù)計(jì)審稿時(shí)間：

Memes have been defined as basic units of transferrable information that reside in the brain and are propagated across populations through the process of imitation. From an algorithmic point of view, memes have come to be regarded as building-blocks of prior knowledge, expressed in arbitrary computational representations (e.g., local search heuristics, fuzzy rules, neural models, etc.), that have been acquired through experience by a human or machine, and can be imitated (i.e., reused) across problems.

The Memetic Computing journal welcomes papers incorporating the aforementioned socio-cultural notion of memes into artificial systems, with particular emphasis on enhancing the efficacy of computational and artificial intelligence techniques for search, optimization, and machine learning through explicit prior knowledge incorporation. The goal of the journal is to thus be an outlet for high quality theoretical and applied research on hybrid, knowledge-driven computational approaches that may be characterized under any of the following categories of memetics:

Type 1: General-purpose algorithms integrated with human-crafted heuristics that capture some form of prior domain knowledge; e.g., traditional memetic algorithms hybridizing evolutionary global search with a problem-specific local search.

Type 2: Algorithms with the ability to automatically select, adapt, and reuse the most appropriate heuristics from a diverse pool of available choices; e.g., learning a mapping between global search operators and multiple local search schemes, given an optimization problem at hand.

Type 3: Algorithms that autonomously learn with experience, adaptively reusing data and/or machine learning models drawn from related problems as prior knowledge in new target tasks of interest; examples include, but are not limited to, transfer learning and optimization, multi-task learning and optimization, or any other multi-X evolutionary learning and optimization methodologies.

模因被定義為可轉(zhuǎn)移信息的基本單位，存在于大腦中，并通過(guò)模仿過(guò)程在人群中傳播。從算法的角度來(lái)看，模因已被視為先驗(yàn)知識(shí)的構(gòu)建塊，以任意計(jì)算表示形式（例如，局部搜索啟發(fā)式、模糊規(guī)則、神經(jīng)模型等）表示，這些先驗(yàn)知識(shí)是通過(guò)人類或機(jī)器的經(jīng)驗(yàn)獲得的，并且可以在問(wèn)題中模仿（即重復(fù)使用）。

《模因計(jì)算》雜志歡迎將上述社會(huì)文化模因概念納入人工系統(tǒng)的論文，特別強(qiáng)調(diào)通過(guò)明確的先驗(yàn)知識(shí)整合來(lái)提高計(jì)算和人工智能技術(shù)在搜索、優(yōu)化和機(jī)器學(xué)習(xí)方面的有效性。因此，該期刊的目標(biāo)是成為高質(zhì)量理論和應(yīng)用研究的出口，研究混合的、知識(shí)驅(qū)動(dòng)的計(jì)算方法，這些方法可以歸為以下任何一種模因?qū)W類別：

類型 1：通用算法與人為設(shè)計(jì)的啟發(fā)式方法相結(jié)合，可以捕獲某種形式的先驗(yàn)領(lǐng)域知識(shí)；例如，將進(jìn)化全局搜索與特定于問(wèn)題的局部搜索相結(jié)合的傳統(tǒng)模因算法。

類型 2：能夠從各種可用選項(xiàng)中自動(dòng)選擇、調(diào)整和重用最合適啟發(fā)式方法的算法；例如，在給定優(yōu)化問(wèn)題的情況下，學(xué)習(xí)全局搜索運(yùn)算符和多個(gè)局部搜索方案之間的映射。

類型 3：通過(guò)經(jīng)驗(yàn)自主學(xué)習(xí)的算法，自適應(yīng)地重用從相關(guān)問(wèn)題中提取的數(shù)據(jù)和/或機(jī)器學(xué)習(xí)模型作為新目標(biāo)任務(wù)中的先驗(yàn)知識(shí)；示例包括但不限于遷移學(xué)習(xí)和優(yōu)化、多任務(wù)學(xué)習(xí)和優(yōu)化、或任何其他多X進(jìn)化學(xué)習(xí)和優(yōu)化方法。

《Memetic Computing》(模因計(jì)算)編輯部通訊方式為TIERGARTENSTRASSE 17, HEIDELBERG, GERMANY, D-69121。如果您需要協(xié)助投稿或潤(rùn)稿服務(wù)，您可以咨詢我們的客服老師。我們專注于期刊咨詢服務(wù)十年，熟悉發(fā)表政策，可為您提供一對(duì)一投稿指導(dǎo)，避免您在投稿時(shí)頻繁碰壁，節(jié)省您的寶貴時(shí)間，有效提升發(fā)表機(jī)率，確保SCI檢索（檢索不了全額退款）。我們視信譽(yù)為生命，多方面確保文章安全保密，在任何情況下都不會(huì)泄露您的個(gè)人信息或稿件內(nèi)容。