Selectivity and Shape in the Design of Forward-Forward Goodness Functions
cs.LG, cs.AI, cs.NE
Submitted: 2026-03-28
Updated: 2026-11-05
Terminology
Sources
- How Can We Be So Dense? The Benefits of Using Highly Sparse Representations
- Adaptively Sparse Transformers
- The Forward-Forward Algorithm: Some Preliminary Investigations
- Adam: A Method for Stochastic Optimization
- SymBa: Symmetric Backpropagation-Free Contrastive Learning with Forward-Forward Algorithm for Optimizing Convergence
- Layer Collaboration in the Forward-Forward Algorithm
- Traditional and Heavy-Tailed Self Regularization in Neural Network Models
- From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
- The Predictive Forward-Forward Algorithm
- Sparse Sequence-to-Sequence Models
- Searching for Activation Functions
- Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation
- In Search of Goodness: Large Scale Benchmarking of Goodness Functions for the Forward-Forward Algorithm
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis