Recursive QLSTM with Dynamic Variational Quantum Circuit Adaptation
For researchers in quantum machine learning, this work offers a flexible framework for quantum recurrent learning on time series, but the improvements are incremental and lack concrete numerical gains.
The paper proposes a Recursive QLSTM model that extends QLSTM with metacore-based recursive constructions, and identifies the best-performing architecture through numerical tests. The recursive structure improves temporal information propagation and learning performance.
Recent advances in quantum computing and machine learning have motivated the development of quantum models for sequential data processing. In this paper, we propose a Recursive Quantum Long Short-Term Memory model, or Recursive QLSTM, which extends QLSTM through metacore-based recursive constructions. We numerically test the model under different input sequence lengths, metacore designs, and recursive rules, and identify the best-performing architecture among these variants. For this selected model, we further provide theoretical arguments explaining why its recursive structure improves temporal information propagation and enhances learning performance. Our results suggest that Recursive QLSTM offers a flexible and effective framework for quantum recurrent learning over input time series of various lengths.