Alexey Ya. (Yakovlevich) Chervonenkis and Vladimir N. (Naumovich) Vapnik added several glorious pages to the history of the Institute of Control Sciences. In the early 1960s, they joined Lerner’s Laboratory and became leading experts at the Institute. At that time, the theory of pattern recognition theory gained popularity but was investigated by a few researchers (M.A. Aizerman, M.M. Braverman, L.I. Rozonoer, and M.M. Bongard). From 1962 to 1971, Vapnik and Chervonenkis developed the generalized portrait method for pattern recognition. In 1968, they presented proof for a fundamental result, i.e., the conditions of uniform convergence of relative frequencies to probabilities over an infinite number of events, a generalization of the classical law of large numbers. They established the necessary and sufficient conditions for the uniform convergence of empirical means to expectations over a family of random variables. Currently, these results are widely known, and the concept of the Vapnik—Chervonenkis (VC) dimension has entered the international scientific lexicon. Workshops on the Vapnik—Chervonenkis Dimension were held in Rehovot (Israel, 1995), Edinburgh (Great Britain, 1996), Ma’ale HaHamisha (Israel, 1998), Paris (France, 2003), etc.
From 1971, Vapnik and Chervonenkis continued their research in Petrovskii’s Laboratory. The uniform convergence conditions were adopted to show the convergence of learning methods based on minimizing empirical risk and to obtain estimates of the convergence rate. In particular, the learning methods of this class are applied to design piecewise linear decisive rules minimizing the number of errors on the learning material. Note that neural networks are formal means of implementing such rules. Therefore, the Vapnik—Chervonenkis theory has become popular to analyze the performance of neural networks.
Also, Vapnik and Chervonenkis developed structural risk minimization methods. Nowadays, they are widely used in pattern recognition, regression reconstruction, and inverse problems arising in physics, statistics, and other sciences.
The most significant applications of the generalized portrait and structural risk minimization methods include medical diagnosis and risk group selection. Such a problem was solved jointly with the All-Union Cancer Center, the USSR Academy of Medical Sciences. These methods were also applied in geology: an automatic optimal ore mapping system based on operational exploration data was developed jointly with the Institute of Geology of Ore Deposits, the USSR Academy of Sciences. In 1987, Chervonenkis was awarded the USSR State Prize for the development of this system.
Chervonenkis received a professorship at the Royal Holloway University of London in 2000 but continued his work at the Institute of Control Sciences. He studied the application of pattern recognition methods to genetics (in Great Britain) and the application of mathematical methods to geology and mining (in Russia).
Chervonenkis's main books are as follows:
- Analiz komp’yuternykh dannykh (Analysis of Computer Data), Moscow: Yandex, 2009. — 260 p.;
- Prikladnaya magnitooptika (Applied Magnetooptics), Moscow: Energoatomizdat, 1990. — 320 p. (coauthor V.V. Randoshkin);
- Algoritmy i programmy vosstanovleniya zavisimostei (Algorithms and Programs to Reconstruct Dependences), Moscow: Nauka, 1984. — 816 p. (coauthors V.N. Vapnik, T.G. Glazkova, V.A. Koshcheev, and A.I. Mikhalsky);
- Theorie der Zeichenerkennung, Berlin: Academie-Verlag, 1979. — 343 p. (coauthor W.N. Wapnik);
- Magnitnye materialy dlya mikro-elektroniki (Magnetic Materials for Microelectronics), Moscow: Energiya, 1979. — 216 p. (coauthor A.M. Balbashov);
- Magnitnye kristally v tekhnike (Magnetic Crystals for Engineering), Moscow: Znanie, 1974. — 64 p. (coauthor A.M. Balbashov);
- Teoriya raspoznavaniya obrazov (Theory of Pattern Recognition), Moscow: Nauka, 1974. — 416 p. (coauthor V.N. Vapnik).
These books are presented in the Institute’s database:
https://www.ipu.ru/d7ipu/books_library_grid?combine=Червоненкис
The list of journal papers by Chervonenkis is available at Math-Net.Ru:
https://www.mathnet.ru/php/person.phtml?&personid=51221&option_lang=eng
The list of his papers in Avtomatika i Telemekhanika can be found at:
https://www.mathnet.ru/php/search.phtml?jrnid=at&tjrnid=at&wshow=search&option_lang=eng
For their English versions, see the microfilm collection of Automation and Remote Control (1956—1994):
https://archive.org/details/pub_automation-and-remote-control
and the journal page at SpringerLink (2001—2022):
https://www.springer.com/journal/10513
Chervonenkis’s publications are available at:
https://elibrary.ru/author_items.asp?authorid=597930&pubrole=100&show_refs=1&show_option=0
Browse the Institute’s database as well:
https://www.ipu.ru/pubs?combine=Червоненкис
Also, see the Wikipedia page devoted to Chervonenkis:
https://en.wikipedia.org/wiki/Alexey_Chervonenkis
Scopus Author ID: 56017560700, 7003337055