Lock-in EP: An In-Situ Training Algorithm for Oscillatory Hardware
cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Code: https://github.com/wilkieolin/PhasorNetworks.jl
Sources
- Hyperdimensional Computing Provides a Programming Paradigm for Oscillatory Systems
- Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation
- Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignment
- Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges
- Deep Phasor Networks: Connecting Conventional and Spiking Neural Networks
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