权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

自己組織化による学習：人工知能の新たな基礎を開拓

通过自组织学习：开创人工智能的新基础

基本信息

批准号：
22K19814
负责人：
VARGAS DANILO
金额：
$ 4.16万
依托单位：
Kyushu University
依托单位国家：
日本
项目类别：
Grant-in-Aid for Challenging Research (Exploratory)
财政年份：
2022
资助国家：
日本
起止时间：
2022-06-30 至 2024-03-31
项目状态：
已结题

来源：
https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-22K19814/
关键词：
SyncMap Self-organization Novel AI Paradigm Dynamical systems 自己組織化 Dynamical Equations New Learning Paradigm

项目摘要

In this research we further developed the novel machine learning paradigm based solely on dynamical equations and no optimization. SyncMap was further improved in stability (Symmetrical SyncMap), to deal with high dimensionality (Magnum) and also to work with changing hierarchies (Sigma). Symmetrical SyncMap improves the equations of SyncMap to deal with long-term stability of the initial equations. Magnum uses multiple Inertia-SyncMaps in subsets of variables, enabling it to deal with high dimensional problems. Sigma achieves the astonishing feat of both being accurate enough to predict the structure of hierarchical input structures at the same time as being adaptive enough to deal with changes in them throughout the experiments. All these methods were extensively tested and their results were submitted to top journals in the area. Hopefully, most of them will become available in the next few months.We also developed two key understanding of how input sequences can be used generally to deal with images and other non-sequential input. Based on these new findings, we have proceeded to develop a novel architecture for computer vision and two methodologies for supervised learning classification tasks.

在这项研究中，我们进一步开发了一种新的机器学习范式，它完全基于动力学方程，没有优化。SyncMap在稳定性（对称SyncMap）方面得到了进一步改进，以处理高维（Magnum），并与不断变化的层次结构（Sigma）一起工作。对称SyncMap对SyncMap方程进行了改进，解决了初始方程的长期稳定性问题。Magnum在变量子集中使用多个Inertia-SyncMaps，使其能够处理高维问题。Sigma实现了惊人的壮举，既能准确地预测分层输入结构的结构，同时又能适应整个实验过程中的变化。所有这些方法都经过了广泛的测试，其结果被提交给该领域的顶级期刊。我们还对如何使用输入序列来处理图像和其他非顺序输入有了两个关键的理解。基于这些新发现，我们已经着手开发一种新的计算机视觉架构和两种监督学习分类任务的方法。

项目成果

期刊论文数量（0）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

“Generating oscillation activity with Echo State Network to mimic the behaviour of a simple central pattern generator”

“使用回声状态网络生成振荡活动以模仿简单的中央模式生成器的行为”

DOI：
发表时间：
2023
期刊：
Proceedings of the CogSci 2023
影响因子：
0
作者：
T. Y. Foong;D. V. Vargas
通讯作者：
D. V. Vargas

Curious-II: A Multi/Many-Objective Optimization Algorithm with Subpopulations based on Multi-novelty Search

DOI：
10.1145/3583133.3590543
发表时间：
2023-07
期刊：
Proceedings of the Companion Conference on Genetic and Evolutionary Computation
影响因子：
0
作者：
Yuzi Jiang;Danilo Vasconcellos Vargas
通讯作者：
Yuzi Jiang;Danilo Vasconcellos Vargas

Understanding SyncMap’s Dynamics and Its Self-organization Properties: A Space-time Analysis

了解 SyncMap 的动力学及其自组织特性：时空分析

DOI：
10.1145/3582099.3582102
发表时间：
2022
期刊：
Proceedings of the 2022 5th Artificial Intelligence and Cloud Computing Conference
影响因子：
0
作者：
Heng Zhang;Danilo Vasconcellos Vargas
通讯作者：
Danilo Vasconcellos Vargas

Understanding SyncMap: Analyzing the components of Its Dynamical Equation

理解SyncMap：分析其动态方程的组成部分