Braverman Readings in Machine Learning. Key Ideas from Inception to Current State
This state-of-the-art survey is dedicated to the memory of Emmanuil Markovich Braverman (1931-1977), a pioneer in developing the machine learning theory. The 12 revised full papers and 4 short papers included in this volume were presented at the conference "Braverman Readings in Machine Learning: Key Ideas from Inception to Current State" held in Boston, MA, USA, in April 2017, commemorating the 40th anniversary of Emmanuil Braverman's decease. The papers present an overview of some of Braverman's ideas and approaches. The collection is divided in three parts. The first part bridges the past and the present. Its main contents relate to the concept of kernel function and its application to signal and image analysis as well as clustering. The second part presents a set of extensions of Braverman's work to issues of current interest both in theory and applications of machine learning. The third part includes short essays by a friend, a student, and a colleague.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Potential Functions for Signals and Symbolic Sequences
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
Geometrical Insights for Implicit Generative Modeling
Applications to Physics
Personal and Beyond
A Man of Unlimited Capabilities in Memory of E M Braverman
Braverman and His Theory of Disequilibrium Economics
My Mentor and My Model
List of Bravermans Papers Published in the Avtomatika i telemekhanika Journal Moscow Russia and Translated to English as Automation and Remote...
OneClass Semisupervised Learning
Prediction of Drug Efficiency by Transferring Gene Expression Data from Cell Lines to Cancer Patients
On One Approach to Robot Motion Planning
Other editions - View all
algorithm Alignment Kernel analysis antihydrogen application Automation and Remote Bayesian Braverman causal cell lines classification cluster coefficients complexity computed consider convergence convex dataset decision rule deep neural networks deep reinforcement learning defined depend detector distance function distance space elements embedding estimation Euclidean example ffiffiffiffiffiffiffi finite images inequality inner product K-Means KRRPM Lemma linear space linearly separable machine learning matrix measure methods metric space minimal geodesic Misha motion planning Muchnik neural networks observer optimal parameters particle pattern recognition Polish space positive definite potential functions predictive distributions probabilistic probability problem Proof properties proposed protein random real-world objects regression regularization function reinforcement learning Remote Control representation robot Rozonoer sample Sect similarity sorafenib Springer statistical structure subset support vector machines symbolic sequences symmetric Theorem theory training criterion variables zero