Braverman Readings in Machine Learning. Key Ideas from Inception to Current StateThis 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.
Contents
Potential Functions for Signals and Symbolic Sequences | 3 |
A Unified Framework for Clustering | 32 |
Compactness Hypothesis Potential Functions and Rectifying Linear Space in Machine Learning | 52 |
Conformal Predictive Distributions with Kernels | 103 |
On the Concept of Compositional Complexity | 122 |
On the Choice of a Kernel Function in Symmetric Spaces | 128 |
Causality Modeling and Statistical Generative Mechanisms | 148 |
Novel Developments | 187 |
Geometrical Insights for Implicit Generative Modeling | 229 |
Applications to Physics | 269 |
An Overview | 298 |
Personal and Beyond | 329 |
A Man of Unlimited Capabilities in Memory of E M Braverman | 331 |
Braverman and His Theory of Disequilibrium Economics | 333 |
My Mentor and My Model | 341 |
List of Bravermans Papers Published in the Avtomatika i telemekhanika Journal Moscow Russia and Translated to English as Automation and Remote... | 349 |
OneClass Semisupervised Learning | 188 |
Prediction of Drug Efficiency by Transferring Gene Expression Data from Cell Lines to Cancer Patients | 201 |
On One Approach to Robot Motion Planning | 213 |
| 352 | |
Author Index | 353 |
Other editions - View all
Braverman Readings in Machine Learning. Key Ideas from Inception to Current ... Lev Rozonoer,Boris Mirkin,Ilya Muchnik No preview available - 2018 |
Common terms and phrases
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
Bibliographic information
| Title | Braverman Readings in Machine Learning. Key Ideas from Inception to Current State LNCS sublibrary: Artificial intelligence Volume 11100 of Lecture Notes in Artificial Intelligence Volume 11100 of Lecture notes in computer science Lecture notes in computer science: Lecture notes in artificial intelligence |
| Author | Lev Rozonoer |
| Publisher | Springer, 2018 |
| ISBN | 3319994921, 9783319994925 |
| Length | 353 pages |
| Export Citation | BiBTeX EndNote RefMan |