Function regression using the forward forward training and inferring paradigm
This work addresses function approximation for machine learning applications, introducing a new use case for the Forward-Forward paradigm, but it appears incremental as it adapts an existing method to a new task.
The paper tackles function regression using the Forward-Forward algorithm, a novel training method without backpropagation, and demonstrates its application to univariate and multivariate functions, with preliminary extensions to Kolmogorov Arnold Networks and Deep Physical Neural Networks.
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.