1128 0097-0549/18/4809-1128 ©2018 Springer Science+Business Media, LLC Neuroscience and Behavioral Physiology, Vol. 48, No. 9, November, 2018 Introduction. The development of noninvasive brain– computer interfaces (BCI) is a popular research theme in current neurophysiology; thee are currently many imple- mentations of BCI addressing different tasks and differing in terms of various characteristics such as the brain activity re- cording technology used, the electrophysiological phenom- enon underlying command formation, and the algorithms used for signal processing and data analysis. One of the key characteristics determining the possible areas of application of these systems is the electrophysiological process used to generate the control signal. The phenomena which can be used for this purpose include imposition of a neuron activa- tion rhythm on the primary visual cortex [Won et al., 2014], the appearance of the P300 potential in responses to chang- es in the field of attention [Farwell and Donchin, 1988], the occurrence of slow cortical potentials [Hinterburger et al., 2004], the appearance of a readiness potential before onset of a motor act [Krauledat et al., 2004], and desynchroniza- tion and synchronization of sensorimotor rhythms accom- panied by performed or imagined movements [Blankertz et al., 2006]. The Brain–Computer Interface: Experience of Construction, Use, and Potential Routes to Improving Performance K. V. Volkova, 1 N. I. Dagaev, 1 A. S. Kiselev, 2 V. R. Kasumov, 3 M. V. Aleksandrov, 3 and A. E. Osadchiy 1 UDC 621.821 Translated from Zhurnal Vysshei Nervnoi Deyatel’nosti imeni I. P. Pavlova, Vol. 67, No. 4, pp. 504–520, July–August, 2017. Original article submitted March 13, 2017. Accepted May 3, 2017. Neurocomputer interfaces or, as they have come to be known in the Russian literature, brain–computer in- terfaces (BCI), are used in several areas and have the potential for uses in solving both research and applied tasks. Pilot studies in the clinical application of BCI to poststroke neurorehabilitation are currently under way [Frolov et al., 2013; Ang et al., 2010], and there are prospects for the use of BCI for direct restoration of movement/communication capabilities by creating an alternative information exchange channel with intel- ligent prostheses and the surroundings. Studies using electrophysiological data generate the need to process multidimensional, nonstationary signals, reflecting complex physiological processes. Interfaces based on noninvasive technologies for recording brain activity do not as yet provide reliable information links with the user’s brain. The results of our studies show that improvements in the working characteristics of these systems can be obtained by constructing new machine learning algorithms considering the physiological and psychoemotional characteristics of BCI use. These algorithms can be developed either in the classical Bayesian paradigm or using state-of-the-art deep learning techniques. In addition, the creation of methods for the physiological interpretation of nonlinear decision rules found by multilayered structures opens up new potentials for the automatic and objective extraction of knowledge from experimental neurophysi- ological data. Despite the attractiveness of noninvasive technologies, radical increases in the throughput of BCI communication channels and the use of this technology to control prostheses can only be obtained using invasive methods of recording brain activity. Electrocorticograms (ECoG) are the least invasive of these technologies, and in the concluding part of this work we will demonstrate that ECoG can be used for decoding of the kinematic characteristics of finger movements. Keywords: brain–computer interface, EEG, ECoG, deep learning, sensorimotor rhythm. 1 Center for Neuroeconomics and Cognitive Research, National Research University Higher School of Economics, Moscow, Russia; e-mail: voxxys@gmail.com. 2 Moscow Institute of Physics and Technology (State University), Dolgoprudnyi, Moscow Oblast, Russia. 3 Polenov Russian Neurosurgical Research Institute, Branch of Almazov North-West Federal Medical Research Center, St. Petersburg, Russia. DOI 10.1007/s11055-018-0677-2