Quantum continual learning on a programmable superconducting processor

Abstract

Quantum computers may outperform classical computers on machine learning tasks. In recent years, a variety of quantum algorithms promising unparalleled potential to enhance, speed up, or innovate machine learning have been proposed. Yet, quantum learning systems, similar to their classical counterparts, may likewise suffer from the catastrophic forgetting problem, where training a model with new tasks would result in a dramatic performance drop for the previously learned ones. This problem is widely believed to be a crucial obstacle to achieving continual learning of multiple sequential tasks. Here, we report an experimental demonstration of quantum continual learning on a fully programmable superconducting processor. In particular, we sequentially train a quantum classifier with three tasks, two about identifying real-life images and the other on classifying quantum states, and demonstrate its catastrophic forgetting through experimentally observed rapid performance drops for prior tasks. To overcome this dilemma, we exploit the elastic weight consolidation strategy and show that the quantum classifier can incrementally learn and retain knowledge across the three distinct tasks, with an average prediction accuracy exceeding 92.3%. In addition, for sequential tasks involving quantum-engineered data, we demonstrate that the quantum classifier can achieve a better continual learning performance than a commonly used classical feedforward network with a comparable number of variational parameters. Our results establish a viable strategy for empowering quantum learning systems with desirable adaptability to multiple sequential tasks, marking an important primary experimental step towards the long-term goal of achieving quantum artificial general intelligence.

21 pages, 14 figures

References in corpus (35)

• Quantum Computing in the NISQ era and beyond
• Overcoming catastrophic forgetting in neural networks
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum Machine Learning
• Quantum algorithm for solving linear systems of equations
• Supervised learning with quantum enhanced feature spaces
• Quantum computational advantage using photons
• Barren plateaus in quantum neural network training landscapes
• Noisy intermediate-scale quantum (NISQ) algorithms
• Quantum Circuit Learning
• Quantum principal component analysis
• Error mitigation for short-depth quantum circuits
• Quantum Error Correction for Quantum Memories
• Strong quantum computational advantage using a superconducting quantum processor
• Suppressing quantum errors by scaling a surface code logical qubit
• Logical quantum processor based on reconfigurable atom arrays
• Quantum random access memory
• Challenges and Opportunities in Quantum Machine Learning
• Quantum error correction below the surface code threshold
• Quantum generative adversarial learning
• A rigorous and robust quantum speed-up in supervised machine learning
• The Expressive Power of Parameterized Quantum Circuits
• Hybrid Quantum-Classical Approach to Quantum Optimal Control
• Continual Learning of Context-dependent Processing in Neural Networks
• Barren Plateaus in Variational Quantum Computing
• Quantum machine learning beyond kernel methods
• Quantum generative adversarial learning in a superconducting quantum circuit
• Machine learning meets quantum physics
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• Statistical mechanics of the Cluster-Ising model
• Experimental quantum adversarial learning with programmable superconducting qubits
• Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence
• Classical surrogates for quantum learning models
• Quantum neural networks form Gaussian processes
• Quantum Continual Learning Overcoming Catastrophic Forgetting