Supervised Learning with Quantum Computers

Introduction.- Background.- How quantum computers can classify data.- Organisation of the book.- Machine Learning.- Prediction.- Models.- Training.- Methods in machine learning.- Quantum Information.- Introduction to quantum theory.- Introduction to quantum computing.- An example: The Deutsch-Josza algorithm.- Strategies of information encoding.- Important quantum routines.- Quantum advantages.- Computational complexity of learning.- Sample complexity.- Model complexity.- Information encoding.- Basis encoding.- Amplitude encoding.- Qsample encoding.- Hamiltonian encoding.- Quantum computing for inference.- Linear models.- Kernel methods.- Probabilistic models.- Quantum computing for training.- Quantum blas.- Search and amplitude amplification.- Hybrid training for variational algorithms.- Quantum adiabatic machine learning.- Learning with quantum models.- Quantum extensions of Ising-type models.- Variational classifiers and neural networks.- Other approaches to buildquantum models.- Prospects for near-term quantum machine learning.- Small versus big data.- Hybrid versus fully coherent approaches.- Qualitative versus quantitative advantages.- What machine learning can do for quantum computing.- References.

Este título pertence ao(s) assunto(s) indicados(s). Para ver outros títulos clique no assunto desejado.

• Reconhecimento de padrões
• Teoria matemática da computação
• A física quântica (mecânica quântica e teoria quântica de campos)
• Física Matemática
• Robótica

quantum phase estimation;quantum walks;quantum annealing;hidden Markov models;belief nets;Boltzmann machines;adiabatic quantum computing;Grover search;Hopfield models;Quantum inference;Artificial neural network;near term application;Quantum machine learning;data driven prediction;Qsample encoding;quantum gates;Deutsch-Josza algorithm;Kernel methods;quantum blas