Models of quantum «strong» computational intelligence and quantum neural networks of deep learning: platform for intelligent control of industrial robotic sociotechnical systems

The principles and methods of quantum «strong» computational intelligence model’s design based on the tools of quantum deep learning applying quantum neural networks and a quantum genetic algorithm are considered. Additional features of quantum perceptron models and quantum deep learning engineering models are discussed when using QCOptKBTM - knowledge base optimization toolkit for intelligent controllers in the tasks of quantum intelligent control of robotic sociotechnical systems in projects «Industry 4.0 / 5.0 /6.0». The description of the features of quantum deep learning allows to more accurately and deeply master the capabilities of the QCOptKBTM toolkit, which includes the stages of learning and extracting (from source data) a learning signal using the SCOptKBTM toolkit based on soft computing technology, and is further considered as classical data. Due to quantum computing operators, classical data is encoded by qubits, the optimal choice of quantum correlation between the desired solutions and the use of constructive interference is made, the desired result is extracted by measurement. Thus, the developed intelligent SCOptKBTM and QCOptKBTM tools include the principles of quantum deep learning, and, as in the case of soft computing technology, forms the optimal structure of the new quantum neural network, and through the use of a quantum genetic algorithm accelerates the search for the desired solution.