Quantum Long Short-Term Memory
This work addresses the challenge of implementing machine learning algorithms on noisy intermediate-scale quantum devices, offering a potential incremental improvement for quantum computing applications in sequence modeling.
The authors tackled the problem of modeling temporal data by proposing a hybrid quantum-classical LSTM model, demonstrating that it learns various temporal data types and, in certain cases, converges faster or achieves better accuracy than classical LSTM.
Long short-term memory (LSTM) is a kind of recurrent neural networks (RNN) for sequence and temporal dependency data modeling and its effectiveness has been extensively established. In this work, we propose a hybrid quantum-classical model of LSTM, which we dub QLSTM. We demonstrate that the proposed model successfully learns several kinds of temporal data. In particular, we show that for certain testing cases, this quantum version of LSTM converges faster, or equivalently, reaches a better accuracy, than its classical counterpart. Due to the variational nature of our approach, the requirements on qubit counts and circuit depth are eased, and our work thus paves the way toward implementing machine learning algorithms for sequence modeling on noisy intermediate-scale quantum (NISQ) devices.