Learning Hierarchically-Structured Concepts II: Overlapping Concepts, and Networks With Feedback
Learning Hierarchically-Structured Concepts II: Overlapping Concepts, and Networks With Feedback
复制标题
DOI：
10.48550/arxiv.2304.09540
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Nancy A. Lynch;Frederik Mallmann-Trenn
中科院分区：
文献类型：
--
作者：
Nancy A. Lynch;Frederik Mallmann-Trenn
我们继续 Lynch 和 Mallmann-Trenn（神经网络，2021）的研究，研究如何在类脑神经网络中表示具有层次结构的概念，如何使用这些表示来识别概念，以及如何学习这些表示。在 Lynch 和 Mallmann-Trenn（神经网络，2021）中，我们考虑了简单的树结构概念和前馈分层网络。在这里，我们以两种方式扩展模型：我们允许不同概念的子代之间有限的重叠，并且我们允许网络包含反馈边缘。对于这些更一般的情况，我们描述和分析识别算法和学习算法。
We continue our study from Lynch and Mallmann-Trenn (Neural Networks, 2021), of how concepts that have hierarchical structure might be represented in brain-like neural networks, how these representations might be used to recognize the concepts, and how these representations might be learned. In Lynch and Mallmann-Trenn (Neural Networks, 2021), we considered simple tree-structured concepts and feed-forward layered networks. Here we extend the model in two ways: we allow limited overlap between children of different concepts, and we allow networks to include feedback edges. For these more general cases, we describe and analyze algorithms for recognition and algorithms for learning.