Quantum Deep Learning
read the original abstract
In recent years, deep learning has had a profound impact on machine learning and artificial intelligence. At the same time, algorithms for quantum computers have been shown to efficiently solve some problems that are intractable on conventional, classical computers. We show that quantum computing not only reduces the time required to train a deep restricted Boltzmann machine, but also provides a richer and more comprehensive framework for deep learning than classical computing and leads to significant improvements in the optimization of the underlying objective function. Our quantum methods also permit efficient training of full Boltzmann machines and multi-layer, fully connected models and do not have well known classical counterparts.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
Breaking QAOA's Fixed Target Hamiltonian Barrier: A Fully Connected Quantum Boltzmann Machine via Bilevel Optimization
A bilevel optimization method turns QAOA into a fully connected QBM that achieves 0.9559 target state probability noiseless and retains top probability under realistic noise levels.
-
Quantum Data Fitting Algorithm for Non-sparse Matrices
Quantum data fitting algorithm for non-sparse N x N Hermitian matrices achieves O(κ² √N polylog(N) / (ε log κ)) runtime via QSVE, eigenvalue sign recovery, and regularization.
-
Implementation of a Hamming-Distance-Like Genomic Quantum Classifier Using Inner Products on IBMQX4 and IBMQX16
Quantum circuits implement Hamming-distance-like genomic classifiers via active and symmetric inner products on IBM quantum processors with fixed qubit requirements for arbitrary training samples.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.