Accelerating the training of single-layer binary neural networks using the HHL quantum algorithm
arXiv:2210.12707 · doi:10.1109/ICCD56317.2022.00070
Abstract
Binary Neural Networks are a promising technique for implementing efficient deep models with reduced storage and computational requirements. The training of these is however, still a compute-intensive problem that grows drastically with the layer size and data input. At the core of this calculation is the linear regression problem. The Harrow-Hassidim-Lloyd (HHL) quantum algorithm has gained relevance thanks to its promise of providing a quantum state containing the solution of a linear system of equations. The solution is encoded in superposition at the output of a quantum circuit. Although this seems to provide the answer to the linear regression problem for the training neural networks, it also comes with multiple, difficult-to-avoid hurdles. This paper shows, however, that useful information can be extracted from the quantum-mechanical implementation of HHL, and used to reduce the complexity of finding the solution on the classical side.
arXiv commentAccepted in the 40th IEEE International Conference on Computer Design (ICCD'22). 9 pages, 8 figures, IEEEtran V1.8b
References in corpus (14)
- Quantum Computing in the NISQ era and beyond
- Quantum algorithm for solving linear systems of equations
- A Quantum Approximate Optimization Algorithm
- Deep Neural Networks as Gaussian Processes
- Large-scale photonic Ising machine by spatial light modulation
- Computational Role of Multiqubit Tunneling in a Quantum Annealer
- Quantum Digital Signatures
- QUBO Formulations for Training Machine Learning Models
- Experimental realization of quantum algorithm for solving linear systems of equations
- Gaussian Process Behaviour in Wide Deep Neural Networks
- Verification of Many-Qubit States
- Bayesian Deep Learning on a Quantum Computer
- Quantum Circuit Design for Solving Linear Systems of Equations
- Defence against adversarial attacks using classical and quantum-enhanced Boltzmann machines