- Author Sri Amit Ray
About this book
The book examined limitations and advantages of different machine learning algorithms in classical and quantum computing frameworks. It explained the ways to leverage the quantum properties of coherence, superposition, entanglement, and tunneling in the context of machine learning and artificial intelligence applications. It explained the ten key properties of quantum machine learning. The book explained in depth the concepts of Quantum Algorithms, Quantum Programming, Quantum Neural Networks, Quantum Parametric Circuits, Quantum back-propagation principles, Quantum Support Vector Machines, Quantum CNN, Quantum Restricted Boltzmann Machines, Quantum LSTM, Quantum RNN, Quantum Deep Learning and Quantum Reinforcement Learning.
The book explained, details of Quantum Monte Carlo Tree Search (QMCTS), the quantum adaptive multi-stage sampling simulation optimization algorithm and its uses for estimating value functions through finite-horizon Quantum Markov decision processes (QMDPs). There are four main stages of our QMCTS are selection, expansion, simulation and backpropagation. Quantum selection and quantum backpropgation are key algorithms of our QMCTS framework.
It also explains the details of Quantum Principal Component Analysis, Quantum State Learning, Quantum Meta-Learning (QML), Quantum Dynamical Descent (QDD), Quantum Approximate Optimization Algorithm (QAOA), Quantum Adiabatic Algorithm (QAA). Finally, the book discuses the Quantum Learning in different hybrid architectures.
Related courses
Artificial Intelligence Master Course Algorithms and Applications
AI algorithms and their applications.