Reshaping the Forward-Forward Algorithm with a Similarity-Based Objective
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911147879301120 |
|---|---|
| author | Gong, James Luo, Raymond Wang, Emma Ge, Leon Li, Bruce Marattukalam, Felix Abdulla, Waleed |
| author_facet | Gong, James Luo, Raymond Wang, Emma Ge, Leon Li, Bruce Marattukalam, Felix Abdulla, Waleed |
| contents | Backpropagation is the pivotal algorithm underpinning the success of artificial neural networks, yet it has critical limitations such as biologically implausible backward locking and global error propagation. To circumvent these constraints, the Forward-Forward algorithm was proposed as a more biologically plausible method that replaces the backward pass with an additional forward pass. Despite this advantage, the Forward-Forward algorithm significantly trails backpropagation in accuracy, and its optimal form exhibits low inference efficiency due to multiple forward passes required. In this work, the Forward-Forward algorithm is reshaped through its integration with similarity learning frameworks, eliminating the need for multiple forward passes during inference. This proposed algorithm is named Forward-Forward Algorithm Unified with Similarity-based Tuplet loss (FAUST). Empirical evaluations on MNIST, Fashion-MNIST, and CIFAR-10 datasets indicate that FAUST substantially improves accuracy, narrowing the gap with backpropagation. On CIFAR-10, FAUST achieves 56.22\% accuracy with a simple multi-layer perceptron architecture, approaching the backpropagation benchmark of 57.63\% accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_08697 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reshaping the Forward-Forward Algorithm with a Similarity-Based Objective Gong, James Luo, Raymond Wang, Emma Ge, Leon Li, Bruce Marattukalam, Felix Abdulla, Waleed Machine Learning Artificial Intelligence Backpropagation is the pivotal algorithm underpinning the success of artificial neural networks, yet it has critical limitations such as biologically implausible backward locking and global error propagation. To circumvent these constraints, the Forward-Forward algorithm was proposed as a more biologically plausible method that replaces the backward pass with an additional forward pass. Despite this advantage, the Forward-Forward algorithm significantly trails backpropagation in accuracy, and its optimal form exhibits low inference efficiency due to multiple forward passes required. In this work, the Forward-Forward algorithm is reshaped through its integration with similarity learning frameworks, eliminating the need for multiple forward passes during inference. This proposed algorithm is named Forward-Forward Algorithm Unified with Similarity-based Tuplet loss (FAUST). Empirical evaluations on MNIST, Fashion-MNIST, and CIFAR-10 datasets indicate that FAUST substantially improves accuracy, narrowing the gap with backpropagation. On CIFAR-10, FAUST achieves 56.22\% accuracy with a simple multi-layer perceptron architecture, approaching the backpropagation benchmark of 57.63\% accuracy. |
| title | Reshaping the Forward-Forward Algorithm with a Similarity-Based Objective |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2509.08697 |