Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Time-warping invariant quantum recurrent neural networks via quantum-classical adaptive gating

Journal Article · · Machine Learning: Science and Technology
ORCiD logo [1];  [2];  [3];  [4]
  1. Eindhoven University of Technology (Netherlands)
  2. King's College, London (United Kingdom)
  3. University of Florence (Italy); Istituto Nazionale di Fisica Nucleare (INFN), Sesto Fiorentino (Italy)
  4. DeepMind, London (United Kingdom)
+ Show Author Affiliations

Adaptive gating plays a key role in temporal data processing via classical recurrent neural networks (RNNs), 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 RNNs (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.

Research Organization:
Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
Sponsoring Organization:
USDOE Office of Science (SC), High Energy Physics (HEP); European Union's Horizon 2020; Engineering and Physical Sciences Research Council (EPSRC)
Grant/Contract Number:
AC02-07CH11359
OSTI ID:
1923309
Report Number(s):
FERMILAB-PUB--23-021-SQMS-V; arXiv:2301.08173; {"Journal ID: ISSN 2632-2153",oai:inspirehep.net:2624774}
Journal Information:
Machine Learning: Science and Technology, Journal Name: Machine Learning: Science and Technology Journal Issue: 4 Vol. 4; ISSN 2632-2153
Publisher:
IOP PublishingCopyright Statement
Country of Publication:
United States
Language:
English

References (19)

Quantum simulation journal March 2014
Extreme Dimensionality Reduction with Quantum Modeling journal December 2020
Trainability of Dissipative Perceptron-Based Quantum Neural Networks journal May 2022
Quantum Adaptive Agents with Efficient Long-Term Memories journal January 2022
Quantum collision models: Open system dynamics from repeated interactions journal April 2022
Absence of Barren Plateaus in Quantum Convolutional Neural Networks journal October 2021
Temporal Information Processing on Noisy Quantum Computers journal August 2020
Modelling non-markovian quantum processes with recurrent neural networks journal December 2018
Quantum advantage in learning from experiments journal June 2022
Simple statistical gradient-following algorithms for connectionist reinforcement learning journal May 1992
Learning temporal data with a variational quantum recurrent neural network journal May 2021
Pseudo maximum likelihood approach for the analysis of multivariate left‐censored longitudinal data journal August 2016
Measuring Analytic Gradients of General Quantum Evolution with the Stochastic Parameter Shift Rule journal January 2021
QuTiP: An open-source Python framework for the dynamics of open quantum systems journal August 2012
Advances in natural language processing journal July 2015
Quantum circuit learning journal September 2018
Group-Invariant Quantum Machine Learning journal September 2022
Approximation of quantum control correction scheme using deep neural networks journal March 2019
SciPy 1.0: fundamental algorithms for scientific computing in Python journal February 2020

Similar Records

Related Subjects

97
quantum machine learning
recurrent models
time-warping