New approaches to the approximation of solutions in machine learning

Machine learning tasks focused on determining the laws of control of robots with complex locomotion are considered. The exponential computational complexity of such tasks is shown when using existing methods, in particular, reinforcement learning. The theoretical possibility of finding a multidimensional control function based on differential-algebraic equations of the dynamics of such systems is substantiated by varying the selected subset of the coupling equations. The possibility of a significant reduction in the dimension of the parameter space of the optimization problem on this basis is analyzed. Examples of the proposed method use for solving problems of the dynamics of machines, zoomorphic and anthropomorphic robots are given. The compatibility of the proposed mathematical method with neuromorphic dynamic systems used as a kernel in reservoir computing is shown. The fundamental admissibility of designing hardware for implementing reservoir computing on this basis is shown.