Self-Modulating Quantum Fast-Weight Programmers for Efficient Adaptive Sequential Learning
The paper proposes Self-Modulating QFWP, a quantum machine learning model that improves convergence stability and prediction performance on time-series data.
The paper introduces a novel mechanism for adaptive modulation in quantum machine learning, which improves convergence stability and prediction performance compared to prior work.
Before reading this…
Applications
- →Time-series forecasting
- →Quantum machine learning
To understand this paper, make sure you know these concepts first:
- Quantum machine learningfind papers →
- Time-series data processingfind papers →
Abstract
More Like ThisRecent advances in quantum machine learning have motivated efficient models for sequential data processing. In this paper, we propose Self-Modulating Quantum Fast Weight Programmers, or Self-Modulating QFWP, which extends Quantum Fast Weight Programmers by introducing adaptive modulation over both newly generated fast-weight updates and historical fast-weight memory. Numerical results show that the proposed mechanism improves convergence stability and prediction performance across varying model settings, including different numbers of qubits and input sequence lengths. We further provide theoretical arguments explaining how self-modulation balances new information injection with memory retention, thereby enhancing temporal information propagation. These results suggest that Self-Modulating QFWP is a compact and effective framework for quantum machine learning on time-series data.