quantum-deep-neural-network
Quantum algorithm to train an infinite-width deep neural network
view repo
Given the success of deep learning in classical machine learning, quantum algorithms for traditional neural network architectures may provide one of the most promising settings for quantum machine learning. Considering a fully-connected feedforward neural network, we show that conditions amenable to classical trainability via gradient descent coincide with those necessary for efficiently solving quantum linear systems. We propose a quantum algorithm to approximately train a wide and deep neural network up to O(1/n) error for a training set of size n by performing sparse matrix inversion in O(log n) time. To achieve an end-to-end exponential speedup over gradient descent, the data distribution must permit efficient state preparation and readout. We numerically demonstrate that the MNIST image dataset satisfies such conditions; moreover, the quantum algorithm matches the accuracy of the fully-connected network. Beyond the proven architecture, we provide empirical evidence for O(log n) training of a convolutional neural network with pooling.
READ FULL TEXT
We develop a new quantum neural network layer designed to run efficientl...
read it
It was conjectured that any neural network of any structure and arbitrar...
read it
Variational Bayes (VB) is a critical method in machine learning and
stat...
read it
Understanding how the D-Wave quantum computer could be used for machine
...
read it
Quantum machine learning has the potential for broad industrial applicat...
read it
We provide a characterization of two types of directed homology for
full...
read it
We use a quantum annealing D-Wave 2X computer to obtain solutions to NP-...
read it
Quantum algorithm to train an infinite-width deep neural network
Comments
There are no comments yet.