Cyclic Neural Network

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Liangwei, Zhang, Hengrui, Song, Zihe, Zhang, Jiawei, Zhang, Weizhi, Ma, Jing, Yu, Philip S.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910318928592896
author Yang, Liangwei
Zhang, Hengrui
Song, Zihe
Zhang, Jiawei
Zhang, Weizhi
Ma, Jing
Yu, Philip S.
author_facet Yang, Liangwei
Zhang, Hengrui
Song, Zihe
Zhang, Jiawei
Zhang, Weizhi
Ma, Jing
Yu, Philip S.
contents This paper answers a fundamental question in artificial neural network (ANN) design: We do not need to build ANNs layer-by-layer sequentially to guarantee the Directed Acyclic Graph (DAG) property. Drawing inspiration from biological intelligence (BI), where neurons form a complex, graph-structured network, we introduce the groundbreaking Cyclic Neural Networks (Cyclic NNs). It emulates the flexible and dynamic graph nature of biological neural systems, allowing neuron connections in any graph-like structure, including cycles. This offers greater adaptability compared to the DAG structure of current ANNs. We further develop the Graph Over Multi-layer Perceptron, which is the first detailed model based on this new design paradigm. Experimental validation of the Cyclic NN's advantages on widely tested datasets in most generalized cases, demonstrating its superiority over current BP training methods through the use of a forward-forward (FF) training algorithm. This research illustrates a totally new ANN design paradigm, which is a significant departure from current ANN designs, potentially leading to more biologically plausible AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03332
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cyclic Neural Network
Yang, Liangwei
Zhang, Hengrui
Song, Zihe
Zhang, Jiawei
Zhang, Weizhi
Ma, Jing
Yu, Philip S.
Neural and Evolutionary Computing
Machine Learning
This paper answers a fundamental question in artificial neural network (ANN) design: We do not need to build ANNs layer-by-layer sequentially to guarantee the Directed Acyclic Graph (DAG) property. Drawing inspiration from biological intelligence (BI), where neurons form a complex, graph-structured network, we introduce the groundbreaking Cyclic Neural Networks (Cyclic NNs). It emulates the flexible and dynamic graph nature of biological neural systems, allowing neuron connections in any graph-like structure, including cycles. This offers greater adaptability compared to the DAG structure of current ANNs. We further develop the Graph Over Multi-layer Perceptron, which is the first detailed model based on this new design paradigm. Experimental validation of the Cyclic NN's advantages on widely tested datasets in most generalized cases, demonstrating its superiority over current BP training methods through the use of a forward-forward (FF) training algorithm. This research illustrates a totally new ANN design paradigm, which is a significant departure from current ANN designs, potentially leading to more biologically plausible AI systems.
title Cyclic Neural Network
topic Neural and Evolutionary Computing
Machine Learning
url https://arxiv.org/abs/2402.03332