QUANT-PHLGJul 19, 2021

Quantum Deep Learning: Sampling Neural Nets with a Quantum Annealer

arXiv:2107.08710v1
Originality Incremental advance
AI Analysis

This work addresses the computational bottleneck of sampling in neural networks for high-resolution image classification, offering a potential speedup for AI applications.

The researchers tackled the problem of slow sampling in deep neural networks by framing them as energy-based models processable on a quantum annealer, achieving a classification speedup of at least one order of magnitude.

We demonstrate the feasibility of framing a classically learned deep neural network as an energy based model that can be processed on a one-step quantum annealer in order to exploit fast sampling times. We propose approaches to overcome two hurdles for high resolution image classification on a quantum processing unit (QPU): the required number and binary nature of the model states. With this novel method we successfully transfer a convolutional neural network to the QPU and show the potential for classification speedup of at least one order of magnitude.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes