提出无需反向传播的函数回归新方法，适用于类脑计算。
Function regression using the forward forward training and inferring paradigm
- 用前向-前向训练替代反向传播进行函数拟合
- 在单变量与多变量函数上验证了良好逼近效果
- 为神经网络物理实现和科尔莫戈罗夫网络提供新思路
函数回归/逼近是机器学习的基础应用。传统神经网络可通过足够多的神经元和训练轮次实现高效函数回归。前向-前向（Forward-Forward）训练算法是一种无需反向传播的新神经网络训练方法，特别适合于类脑计算和神经网络的物理模拟实现。据作者所知，当前前向-前向范式仅限于分类任务。本文提出一种基于前向-前向算法的函数回归新方法，并在单变量和多变量函数上进行了评估。此外，还初步研究了该方法扩展至科尔莫戈罗夫-阿诺德网络（Kolmogorov Arnold Networks）和深度物理神经网络（Deep Physical Neural Networks）的可能性。
原文摘要 · Abstract (English)
Function regression/approximation is a fundamental application of machine learning. Neural networks (NNs) can be easily trained for function regression using a sufficient number of neurons and epochs. The forward-forward learning algorithm is a novel approach for training neural networks without backpropagation, and is well suited for implementation in neuromorphic computing and physical analogs for neural networks. To the best of the authors' knowledge, the Forward Forward paradigm of training and inferencing NNs is currently only restricted to classification tasks. This paper introduces a new methodology for approximating functions (function regression) using the Forward-Forward algorithm. Furthermore, the paper evaluates the developed methodology on univariate and multivariate functions, and provides preliminary studies of extending the proposed Forward-Forward regression to Kolmogorov Arnold Networks, and Deep Physical Neural Networks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。