Braverman Readings in Machine Learning. Key Ideas from Inception to Current State

Potential Functions for Signals and Symbolic Sequences.- Braverman's Spectrum and Matrix Diagonalization versus iK-Means: A Unified Framework for Clustering.-  Compactness Hypothesis, Potential Functions, and Rectifying Linear Space in Machine Learning.- Conformal Predictive Distributions with Kernels.- On the Concept of Compositional Complexity.-  On the Choice of a Kernel Function in Symmetric Spaces.- Causality Modeling and Statistical Generative Mechanisms.- One-Class Semi-Supervised Learning.- Prediction of Drug Efficiency by Transferring Gene Expression Data from Cell Lines to Cancer Patients.- On One Approach to Robot Motion Planning.- Geometrical Insights for Implicit Generative Modeling.- Deep Learning in the Natural Sciences: Applications to Physics.- From Reinforcement Learning to Deep Reinforcement Learning: An Overview.- A Man of Unlimited Capabilities.- Braverman and His Theory of Disequilibrium Economics.- Misha Braverman: My Mentor and My Model.- List of Braverman's papers published in the "Avtomatika itelemekhanika" journal, Moscow, Russia, and translated into English as "Automation and Remote Control" journal.

Lev Rozonoer, West Newton, MA, USA;Boris Mirkin, National Research University Higher School of Economics, Moscow, Russian Federation;Ilya Muchnik, Rutgers University, Piscataway, NJ, USA.