Backpropagation-free Deep Learning for Time-Series Classification
cs.LG, cs.AI
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: 16 pages, 12 figures
Code: https://github.com/sensorlab/bp-free-ts
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline
- Direct Feedback Alignment Provides Learning in Deep Neural Networks
- NoProp: Training Neural Networks without Full Back-propagation or Full Forward-propagation
- The UCR Time Series Archive
- Training Neural Networks with Local Error Signals
- A Time Series Forest for Classification and Feature Extraction
- Decoupled Neural Interfaces using Synthetic Gradients
- Random feedback weights support learning in deep neural networks
- Optuna: A Next-generation Hyperparameter Optimization Framework
- Improved Denoising Diffusion Probabilistic Models
- Principled Training of Neural Networks with Direct Feedback Alignment
Related papers
- 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
- (Mis)generalization of Helpful-Only Fine-tuning