Deep learning

Physics

Dependency (UML)

Qubit

Term (time)

Biology

Algorithm

Recurrent neural network

Long short term memory

Language model

Artificial intelligence

Scale (ratio)

Sequence (biology)

Computer science

Quantum mechanics

Theoretical computer science

Artificial neural network

Genetics

Quantum

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 such as natural language processing, speech recognition on noisy intermediate-scale quantum (NISQ) devices.

Quantum Long Short-Term Memory