Article

Backpropagation-Free Continual Learning: A Unified Energy-Based Framework, Reproducible Benchmark, and Open Challenges

2026-07-08

Abstract excerpt

Backpropagation has been the dominant credit-assignment mechanism behind the deep-learning revolution, yet it is global, memory-hungry, biologically implausible, and costly on hardware dominated by data movement. In parallel, predictive coding, equilibrium propagation, contrastive Hebbian learning and forward-only schemes have shown that useful credit assignment can also arise from local variables and the relaxati...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 70b2d89a-0db5-5d54-b032-89ce103d5281
DOI: 10.20944/preprints202607.0555.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Backpropagation-Free Continual Learning: A Unified Energy-Based Framework, Reproducible Benchmark, and Open ChallengesDOI 10.20944/preprints202607.0555.v1Read

Memory Consolidation with Orthogonal Gradients for avoiding Catastrophic ForgettingSemantic proximity Read

Scaffolded representation learning in deep networksSemantic proximity Read

Training stochastic stabilized supralinear networks by dynamics-neutral growthSemantic proximity Read

What Makes Neural Networks Trainable? Invexity as a Structural Design Principle in AISemantic proximity Read

Overcoming Catastrophic Interference: Neuroscience-inspired Models for Continuous Learning in Neural NetworksSemantic proximity Read

An invariant schema emerges within a neural network during hierarchical learning of visual boundariesSemantic proximity Read

Task-Conditional Accuracy–Support Trade-offs of Sparse Attention Normalizers in Compact ClassifiersSemantic proximity Read

Memory Consolidation with Orthogonal Gradients for avoiding Catastrophic ForgettingSemantic proximity Read

Learning sculpts orthogonal task manifolds for continual skill learning in recurrent networksSemantic proximity Read

A bio-inspired hybrid lifelong learning based on self-selective memristorsSemantic proximity Read

Symbiotic Convolution Block (SCB): An Implicit Feature Recalibration without Attention-Mechanism for Efficient CNNs in Image ClassificationSemantic proximity Read

A biologically inspired architecture with switching units can learn to generalize across backgroundsSemantic proximity Read