Time-Warping Invariant Quantum Recurrent Neural Networks via Quantum-Classical Adaptive Gating
This work addresses the challenge of time-warping invariance in temporal data processing for quantum machine learning, representing an incremental advancement by augmenting existing quantum recurrent neural networks with adaptive gating.
The paper tackled the problem of processing temporal data with invariance to time-warping transformations by introducing a time warping-invariant quantum recurrent neural network (TWI-QRNN) that uses a quantum-classical adaptive gating mechanism, and experimentally demonstrated its capacity to implement such transformations on examples with classical or quantum dynamics.
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.