Quantum continual learning of quantum data realizing knowledge backward transfer

DOI10.1016/J.PHYSA.2023.128779arXiv2203.14032MaRDI QIDQ6158899FDOQ6158899

Authors: Haozhen Situ, Tianxiang Lu, Minghua Pan, Lvzhou Li 

Publication date: 31 May 2023

Published in: Physica A (Search for Journal in Brave)

Abstract: For the goal of strong artificial intelligence that can mimic human-level intelligence, AI systems would have the ability to adapt to ever-changing scenarios and learn new knowledge continuously without forgetting previously acquired knowledge. When a machine learning model is consecutively trained on multiple tasks that come in sequence, its performance on previously learned tasks may drop dramatically during the learning process of the newly seen task. To avoid this phenomenon termed catastrophic forgetting, continual learning, also known as lifelong learning, has been proposed and become one of the most up-to-date research areas of machine learning. As quantum machine learning blossoms in recent years, it is interesting to develop quantum continual learning. This paper focuses on the case of quantum models for quantum data where the computation model and the data to be processed are both quantum. The gradient episodic memory method is incorporated to design a quantum continual learning scheme that overcomes catastrophic forgetting and realizes knowledge backward transfer. Specifically, a sequence of quantum state classification tasks is continually learned by a variational quantum classifier whose parameters are optimized by a classical gradient-based optimizer. The gradient of the current task is projected to the closest gradient, avoiding the increase of the loss at previous tasks, but allowing the decrease. Numerical simulation results show that our scheme not only overcomes catastrophic forgetting, but also realize knowledge backward transfer, which means the classifier's performance on previous tasks is enhanced rather than compromised while learning a new task.

Full work available at URL: https://arxiv.org/abs/2203.14032

Recommendations

• Continuous-variable deep quantum neural networks for flexible learning of structured classical information
• Quantum learning for neural associative memories
• Learning quantum models from quantum or classical data
• Backpropagation training in adaptive quantum networks
• The learnability of quantum states
• Quantum advantage in learning from experiments
• Online learning of quantum states
• Quantum learning algorithms for quantum measurements
• Quantum machine learning based on continuous variable single-photon states: an elementary foundation for quantum neural networks

zbMATH Keywords

quantum machine learningcontinual learningvariational quantum algorithm

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Cites Work

• Deep learning
• Quantum computation and quantum information. 10th anniversary edition
• Quantum recommendation systems
• Overcoming catastrophic forgetting in neural networks
• Quantum generative adversarial network for generating discrete distribution

This page was built for publication: Quantum continual learning of quantum data realizing knowledge backward transfer

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6158899)