经典条件门网络及其学习

IF 2 4区计算机科学 Q3 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

New Generation Computing Pub Date : 2024-04-30 DOI:10.1007/s00354-024-00256-3

Shun-ichi Azuma, Dai Takakura, Ryo Ariizumi, Toru Asai

{"title":"经典条件门网络及其学习","authors":"Shun-ichi Azuma, Dai Takakura, Ryo Ariizumi, Toru Asai","doi":"10.1007/s00354-024-00256-3","DOIUrl":null,"url":null,"abstract":"A research project on chemical AI, called the Molecular Cybernetics Project, was launched in Japan in 2021 with the goal of creating a molecular machine that can learn a type of conditioned reflex through the process of classical conditioning. In this project, we have developed a learning method for the network of such learning molecular machines, which is reported in this paper. First, as a model of a learning molecular machine, we formulate a logic gate that can learn conditioned reflex and introduce the network of the logic gates. Then we derive a key principle for learning, called the flipping principle, by which we present a learning algorithm for the network to realize a desired function.","PeriodicalId":54726,"journal":{"name":"New Generation Computing","volume":"47 1","pages":""},"PeriodicalIF":2.0000,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Networks of Classical Conditioning Gates and Their Learning\",\"authors\":\"Shun-ichi Azuma, Dai Takakura, Ryo Ariizumi, Toru Asai\",\"doi\":\"10.1007/s00354-024-00256-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A research project on chemical AI, called the Molecular Cybernetics Project, was launched in Japan in 2021 with the goal of creating a molecular machine that can learn a type of conditioned reflex through the process of classical conditioning. In this project, we have developed a learning method for the network of such learning molecular machines, which is reported in this paper. First, as a model of a learning molecular machine, we formulate a logic gate that can learn conditioned reflex and introduce the network of the logic gates. Then we derive a key principle for learning, called the flipping principle, by which we present a learning algorithm for the network to realize a desired function.\",\"PeriodicalId\":54726,\"journal\":{\"name\":\"New Generation Computing\",\"volume\":\"47 1\",\"pages\":\"\"},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2024-04-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"New Generation Computing\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1007/s00354-024-00256-3\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"New Generation Computing","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s00354-024-00256-3","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}

引用次数: 0

摘要

2021 年，日本启动了一个名为 "分子控制论项目 "的化学人工智能研究项目，目标是制造出一种分子机器，能够通过经典条件反射过程学习一种条件反射。在该项目中，我们开发了一种用于这种学习型分子机器网络的学习方法，本文对此进行了报道。首先，作为学习型分子机器的模型，我们提出了一种可以学习条件反射的逻辑门，并介绍了逻辑门的网络。然后，我们推导出一个学习的关键原理，即翻转原理，并据此提出了一种网络学习算法，以实现所需的功能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

Networks of Classical Conditioning Gates and Their Learning

查看原文本刊更多论文

Networks of Classical Conditioning Gates and Their Learning

A research project on chemical AI, called the Molecular Cybernetics Project, was launched in Japan in 2021 with the goal of creating a molecular machine that can learn a type of conditioned reflex through the process of classical conditioning. In this project, we have developed a learning method for the network of such learning molecular machines, which is reported in this paper. First, as a model of a learning molecular machine, we formulate a logic gate that can learn conditioned reflex and introduce the network of the logic gates. Then we derive a key principle for learning, called the flipping principle, by which we present a learning algorithm for the network to realize a desired function.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

New Generation Computing 工程技术-计算机：理论方法

CiteScore

5.90

自引率

15.40%

发文量

审稿时长

>12 weeks

期刊介绍： The journal is specially intended to support the development of new computational and cognitive paradigms stemming from the cross-fertilization of various research fields. These fields include, but are not limited to, programming (logic, constraint, functional, object-oriented), distributed/parallel computing, knowledge-based systems, agent-oriented systems, and cognitive aspects of human embodied knowledge. It also encourages theoretical and/or practical papers concerning all types of learning, knowledge discovery, evolutionary mechanisms, human cognition and learning, and emergent systems that can lead to key technologies enabling us to build more complex and intelligent systems. The editorial board hopes that New Generation Computing will work as a catalyst among active researchers with broad interests by ensuring a smooth publication process.