Time-Warping Invariant Quantum Recurrent Neural Networks via Quantum-Classical Adaptive Gating

TL;DR

This paper introduces a novel quantum recurrent neural network model that maintains invariance to time-warping transformations by integrating a quantum-classical adaptive gating mechanism, enhancing temporal data processing capabilities.

Contribution

It proposes the time warping-invariant QRNN (TWI-QRNN), combining quantum memory with adaptive gating to preserve invariance to time warping in sequence processing.

Findings

Successfully demonstrates invariance to time-warping transformations

Capable of handling classical and quantum dynamic sequences

Derived from first principles for theoretical soundness

Abstract

Adaptive gating plays a key role in temporal data processing via classical recurrent neural networks (RNN), as it facilitates retention of past information necessary to predict the future, providing a mechanism that preserves invariance to time warping transformations. This paper builds on quantum recurrent neural networks (QRNNs), a dynamic model with quantum memory, to introduce a novel class of temporal data processing quantum models that preserve invariance to time-warping transformations of the (classical) input-output sequences. The model, referred to as time warping-invariant QRNN (TWI-QRNN), augments a QRNN with a quantum-classical adaptive gating mechanism that chooses whether to apply a parameterized unitary transformation at each time step as a function of the past samples of the input sequence via a classical recurrent model. The TWI-QRNN model class is derived from first principles, and its capacity to successfully implement time-warping transformations is experimentally demonstrated on examples with classical or quantum dynamics.