Forward-Forward algorithm

2 items

RESEARCHarXiv CS.LG·4/16/2026

Sparse Goodness: How Selective Measurement Transforms Forward-Forward Learning

This research systematically studies and enhances the Forward-Forward (FF) algorithm by redesigning its local goodness function, which distinguishes positive from negative data. It introduces 'top-k goodness' and 'entmax-weighted energy,' demonstrating substantial accuracy improvements on benchmarks like Fashion-MNIST.

neural networks goodness function Forward-Forward algorithm deep learning

RESEARCHarXiv CS.LG·20d ago

Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning

This paper introduces Adaptive Multi-Scale Goodness Aggregation (AMSGA), a novel extension of the Forward-Forward (FF) algorithm to enhance stability, robustness, and generalization in local-learning neural networks. AMSGA incorporates multi-scale goodness aggregation, adaptive hard negative mining, and layer-dependent thresholds. Experiments on MNIST and Fashion-MNIST show consistent performance improvements over the baseline FF algorithm.

neural networks Forward-Forward algorithm learning machine learning