Attention-Like Hebbian Learning from Quantum Probability Flow and Quantum-Annealer Tests

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Ohzeki, Masayuki
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917555152617472
author Ohzeki, Masayuki
author_facet Ohzeki, Masayuki
contents We propose a quantum probability-flow principle for deriving local learning rules in associative memory. A transverse field defines leakage channels from data states, and minimizing the measured survival loss gives stability-driven updates. For imaginary-time, dephased dynamics, the local leakage free energy is the log-sum-exp of energy gaps; its gradient is a softmax-weighted Hebbian rule. Real-time stability instead yields a power-law weighting. D-Wave standard- and fast-anneal tests of a one-hot attention forward map are better fitted by an effective softmax than by a Lorentzian power law.
format Preprint
id arxiv_https___arxiv_org_abs_2606_02098
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Attention-Like Hebbian Learning from Quantum Probability Flow and Quantum-Annealer Tests
Ohzeki, Masayuki
Quantum Physics
Disordered Systems and Neural Networks
We propose a quantum probability-flow principle for deriving local learning rules in associative memory. A transverse field defines leakage channels from data states, and minimizing the measured survival loss gives stability-driven updates. For imaginary-time, dephased dynamics, the local leakage free energy is the log-sum-exp of energy gaps; its gradient is a softmax-weighted Hebbian rule. Real-time stability instead yields a power-law weighting. D-Wave standard- and fast-anneal tests of a one-hot attention forward map are better fitted by an effective softmax than by a Lorentzian power law.
title Attention-Like Hebbian Learning from Quantum Probability Flow and Quantum-Annealer Tests
topic Quantum Physics
Disordered Systems and Neural Networks
url https://arxiv.org/abs/2606.02098