{"ID":2838079,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18567","arxiv_id":"2511.18567","title":"In Search of Goodness: Large Scale Benchmarking of Goodness Functions for the Forward-Forward Algorithm","abstract":"The Forward-Forward (FF) algorithm offers a biologically plausible alternative to backpropagation, enabling neural networks to learn through local updates. However, FF's efficacy relies heavily on the definition of \"goodness\", which is a scalar measure of neural activity. While current implementations predominantly utilize a simple sum-of-squares metric, it remains unclear if this default choice is optimal. To address this, we benchmarked 21 distinct goodness functions across four standard image datasets (MNIST, FashionMNIST, CIFAR-10, STL-10), evaluating classification accuracy, energy consumption, and carbon footprint. We found that certain alternative goodness functions inspired from various domains significantly outperform the standard baseline. Specifically, \\texttt{game\\_theoretic\\_local} achieved 97.15\\% accuracy on MNIST, \\texttt{softmax\\_energy\\_margin\\_local} reached 82.84\\% on FashionMNIST, and \\texttt{triplet\\_margin\\_local} attained 37.69\\% on STL-10. Furthermore, we observed substantial variability in computational efficiency, highlighting a critical trade-off between predictive performance and environmental cost. These findings demonstrate that the goodness function is a pivotal hyperparameter in FF design. We release our code on \\href{https://github.com/aryashah2k/In-Search-of-Goodness}{Github} for reference and reproducibility.","short_abstract":"The Forward-Forward (FF) algorithm offers a biologically plausible alternative to backpropagation, enabling neural networks to learn through local updates. However, FF's efficacy relies heavily on the definition of \"goodness\", which is a scalar measure of neural activity. While current implementations predominantly uti...","url_abs":"https://arxiv.org/abs/2511.18567","url_pdf":"https://arxiv.org/pdf/2511.18567v1","authors":"[\"Arya Shah\",\"Vaibhav Tripathi\"]","published":"2025-11-23T18:24:35Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":606734,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2838079,"paper_url":"https://arxiv.org/abs/2511.18567","paper_title":"In Search of Goodness: Large Scale Benchmarking of Goodness Functions for the Forward-Forward Algorithm","repo_url":"https://github.com/aryashah2k/In-Search-of-Goodness","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}