Classifying Data with Local Hamiltonians
arXiv:1807.00804 · doi:10.1142/S0219749918400014
Abstract
The goal of this work is to define a notion of a quantum neural network to classify data, which exploits the low energy spectrum of a local Hamiltonian. As a concrete application, we build a binary classifier, train it on some actual data and then test its performance on a simple classification task. More specifically, we use Microsoft's quantum simulator, Liquid, to construct local Hamiltonians that can encode trained classifier functions in their ground space, and which can be probed by measuring the overlap with test states corresponding to the data to be classified. To obtain such a classifier Hamiltonian, we further propose a training scheme based on quantum annealing which is completely closed-off to the environment and which does not depend on external measurements until the very end, avoiding unnecessary decoherence during the annealing procedure. For a network of size n, the trained network can be stored as a list of O(n) coupling strengths. We address the question of which interactions are most suitable for a given classification task, and develop a qubit-saving optimization for the training procedure on a simulated annealing device. Furthermore, a small neural network to classify colors into red vs. blue is trained and tested, and benchmarked against the annealing parameters.
arXiv comment21 pages, 8 figures, 4 tables
References in corpus (10)
- The quest for a Quantum Neural Network
- Undecidability of the Spectral Gap (short version)
- The power of quantum systems on a line
- Glassy Chimeras could be blind to quantum speedup: Designing better benchmarks for quantum annealing machines
- Power law violation of the area law in quantum spin chains
- Frustration free gapless Hamiltonians for Matrix Product States
- Quantum Proofs
- The Feynman-Kitaev computer's clock: bias, gaps, idling and pulse tuning
- Size-Driven Quantum Phase Transitions
- Translation-Invariant Parent Hamiltonians of Valence Bond Crystals