In memory of Alexei Yakovlevich Chervonenkis
This text in memory of Alexei Yakovlevich was written by Arkady Volozh, co-founder and CEO of Yandex.
On September 22, Alexei Yakovlevich Chervonenkis , a leading employee of the Institute of Control Sciences of the Russian Academy of Sciences, a professor at the Moscow Institute of Physics and Technology and the University of London, a teacher at the School of Data Analysis, who made a huge contribution to machine learning theory, died tragically.
')
The science of machine learning has so far had three periods: precomputer, computer, and the modern period of big data.
The first great work of Chervonenkis and Vapnik was this article, published in 1971. The theory of frequency convergence to their probabilities determined the development of this part of science for several decades ahead.
It was a period of "theoretical" development of machine learning. Then it was possible to count only on some M-200 or, in a good case, on the BESM-ah, therefore there was no talk of "widespread use in the national economy". But to distinguish targets in the air, for example, or to seek out noises on the echo cardiogram, this already helped.
Then came the second stage of the science of machine learning, computer. In the 1990s, people learned, for example, to quite well recognize and digitize texts (including handwritten texts) or clean email from spam. Half of these methods worked on the famous SVM (Support Vector Machine, support vector machine), invented in the early 1990s by Chervonenkis and Vapnik ( VC-Dimension = Vapnik-Chervonenkis dimension). In the mid-2000s, in any well-known office, they worked at SVMs — in our country, in Yukha, in Google, in Amazons, and in Netflix. SVM is described in any tutorial on our topic.
And now came the third era in the development of machine learning: big data and methods of working with them appeared. Now it seems that everything that surrounds us, all objects and services will become a little smarter and will learn to help us in every little thing, foreseeing a little of our desires. This is about how different mechanical and chemical inventions have changed our lives a bit - only now in a bit of a new field.
In the third era, Chervonenkis taught at ShAD-e, and last year at our conference he spoke on the development of his 1971 fundamental work .
Alexey Yakovlevich loved to walk. He walked 20 kilometers a day - in Moscow, in London, in the woods - as he thought. In the summer he had an operation, and he could not walk for three weeks. Then one day he went again - a kilometer, then two, three. And last week he walked his 20 kilometers along the familiar road to Elk Island.
On September 22, Alexei Yakovlevich Chervonenkis , a leading employee of the Institute of Control Sciences of the Russian Academy of Sciences, a professor at the Moscow Institute of Physics and Technology and the University of London, a teacher at the School of Data Analysis, who made a huge contribution to machine learning theory, died tragically.
')
The science of machine learning has so far had three periods: precomputer, computer, and the modern period of big data.
The first great work of Chervonenkis and Vapnik was this article, published in 1971. The theory of frequency convergence to their probabilities determined the development of this part of science for several decades ahead.
It was a period of "theoretical" development of machine learning. Then it was possible to count only on some M-200 or, in a good case, on the BESM-ah, therefore there was no talk of "widespread use in the national economy". But to distinguish targets in the air, for example, or to seek out noises on the echo cardiogram, this already helped.
Then came the second stage of the science of machine learning, computer. In the 1990s, people learned, for example, to quite well recognize and digitize texts (including handwritten texts) or clean email from spam. Half of these methods worked on the famous SVM (Support Vector Machine, support vector machine), invented in the early 1990s by Chervonenkis and Vapnik ( VC-Dimension = Vapnik-Chervonenkis dimension). In the mid-2000s, in any well-known office, they worked at SVMs — in our country, in Yukha, in Google, in Amazons, and in Netflix. SVM is described in any tutorial on our topic.
And now came the third era in the development of machine learning: big data and methods of working with them appeared. Now it seems that everything that surrounds us, all objects and services will become a little smarter and will learn to help us in every little thing, foreseeing a little of our desires. This is about how different mechanical and chemical inventions have changed our lives a bit - only now in a bit of a new field.
In the third era, Chervonenkis taught at ShAD-e, and last year at our conference he spoke on the development of his 1971 fundamental work .
Alexey Yakovlevich loved to walk. He walked 20 kilometers a day - in Moscow, in London, in the woods - as he thought. In the summer he had an operation, and he could not walk for three weeks. Then one day he went again - a kilometer, then two, three. And last week he walked his 20 kilometers along the familiar road to Elk Island.
Source: https://habr.com/ru/post/238545/
All Articles