Generating Sparse Representations Using Quantum Annealing: Comparison to Classical Algorithms


We use a quantum annealing D-Wave 2X (1,152-qubit) computer to generate sparse representations of Canny-filtered, center-cropped 30x30 CIFAR-10 images. Each binary neuron (qubit) represents a feature kernel obtained initially by imprinting on a randomly chosen 5x5 image patch and then adapted via an off-line Hebbian learning protocol using the sparse… (More)
DOI: 10.1109/ICRC.2017.8123653


8 Figures and Tables

Slides referencing similar topics