On Advancements of the Forward-Forward Algorithm

arXiv:2504.21662 · cs.LG · Submitted 2025-04-30 · Read on arXiv

cs.LG

Submitted: 2025-04-30

Updated: 2025-06-25

Code: https://github.com/Xilinx/brevitas

Terminology

• Verification — 1× in this paper · explained in 2 episodes

Sources

• The Forward-Forward Algorithm: Some Preliminary Investigations
• Distance-Forward Learning: Enhancing the Forward-Forward Algorithm Towards High-Performance On-Chip Learning
• The Trifecta: Three simple techniques for training deeper Forward-Forward networks
• Training Convolutional Neural Networks with the Forward-Forward algorithm
• Self-Contrastive Forward-Forward Algorithm
• Parallel Training of Deep Networks with Local Updates
• LightFF: Lightweight Inference for Forward-Forward Algorithm
• Employing Layerwised Unsupervised Learning to Lessen Data and Loss Requirements in Forward-Forward Algorithms

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks