Abstract: We develop an approach to machine learning and anomaly detection via quantum adiabatic evolution. In the training phase we identify an optimal set of weak classifiers, to form a single strong classifier. In the testing phase we adiabatically evolve one or more strong classifiers on a superposition of inputs in order to find certain anomalous elements in the classification space. Both the training and testing phases are executed via quantum adiabatic evolution. We apply and illustrate this approach in detail to the problem of software verification and validation.
Recommendations
Cites work
- scientific article; zbMATH DE number 1804118 (Why is no real title available?)
- scientific article; zbMATH DE number 5320186 (Why is no real title available?)
- scientific article; zbMATH DE number 1332320 (Why is no real title available?)
- scientific article; zbMATH DE number 1950578 (Why is no real title available?)
- A quantum adiabatic evolution algorithm applied to random instances of an NP-complete problem
- Adiabatic approximation with exponential accuracy for many-body systems and quantum computation
- Adiabatic perturbation theory in quantum dynamics
- Arcing classifiers. (With discussion)
- Bounds for the adiabatic approximation with applications to quantum computation
- Efficient feature selection via analysis of relevance and redundancy
- Efficiently checking propositional refutations in HOL theorem provers
- Equivalences and Separations Between Quantum and Classical Learnability
- Graph-Based Algorithms for Boolean Function Manipulation
- Minor-embedding in adiabatic quantum computation. I: The parameter setting problem
- Occam's razor
- On The Number of Symmetry Types of Boolean Functions of n Variables
- Quantum speed-up for unsupervised learning
- Realizable Hamiltonians for universal adiabatic quantum computers
- Supervised machine learning: a review of classification techniques
Cited in
(23)- Blind quantum machine learning based on quantum circuit model
- Quantum Relief algorithm
- Provably efficient machine learning for quantum many-body problems
- Quantum algorithm design: techniques and applications
- Approximate supervised learning of quantum gates via ancillary qubits
- Machine learning entanglement freedom
- Quantum bridge analytics. I: A tutorial on formulating and using QUBO models
- Quantum reservoir computing: a reservoir approach toward quantum machine learning on near-term quantum devices
- Quantum bridge analytics. I: A tutorial on formulating and using QUBO models
- The role of entanglement for enhancing the efficiency of quantum kernels towards classification
- Improved handwritten digit recognition using quantum \(K\)-nearest neighbor algorithm
- Quantum classifier with entangled subgraph states
- Garden optimization problems for benchmarking quantum annealers
- Quantum decision tree classifier
- Quantum classifiers for domain adaptation
- Quantum kernels with Gaussian state encoding for machine learning
- Adiabatic quantum programming: minor embedding with hard faults
- Machine learning versus semidefinite programming approach to a particular problem of the theory of open quantum systems
- Optimal Universal Learning Machines for Quantum State Discrimination
- Quantum AdaBoost algorithm via cluster state
- Quantum-enhanced deliberation of learning agents using trapped ions
- Succinct quantum classification algorithm based on quantum circuit model
- Adjoint-operators and non-adiabatic learning algorithms in neural networks
This page was built for publication: Quantum adiabatic machine learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2393692)
