# Математические методы прогнозирования (лекции, В.В. Стрижов)/Группа 774, осень 2020

(Различия между версиями)
Перейти к: навигация, поиск
 Версия 11:29, 22 декабря 2020 (править)← К предыдущему изменению Версия 11:30, 22 декабря 2020 (править) (отменить)К следующему изменению → Строка 356: Строка 356: #[https://www.mathworks.com/help/signal/ug/autocorrelation-function-of-exponential-sequence.html Autocorrelation Function of Exponential Sequence] #[https://www.mathworks.com/help/signal/ug/autocorrelation-function-of-exponential-sequence.html Autocorrelation Function of Exponential Sequence] #[https://stackoverflow.com/questions/47661872/fast-way-reduce-noise-of-autocorrelation-function-in-python Fast way reduce noise of autocorrelation function in python?] #[https://stackoverflow.com/questions/47661872/fast-way-reduce-noise-of-autocorrelation-function-in-python Fast way reduce noise of autocorrelation function in python?] + + ===Литература к вопросам=== +

## Версия 11:30, 22 декабря 2020

Лекции по четвергам в 10:30 тут: m1p.org/go_zoom

This course joins two parts of the problem statements in Machine Learning. The first part comes from the structure of the measured data. The data come from Physics, Chemistry and Biology and have intrinsic algebraic structure. This stricture is part of the theory that stands behind the measurement. The second part comes from errors of the measurement. The stochastic nature errors request the statistical methods of analysis. So this course joins algebra and statistics. It is devoted to the problem of predictive model selection.

The course holds two semesters: Fall 2020 and Spring 2021. It contains lectures and practical works. Out of schedule cuts off half the score. The scoring, max:

1. Questionnaires during lectures (3)
2. Two application projects (2+2)
3. The final exam: problems with discussion (3)

### Список вопросов и ссылки на материалы курса для зачета

1. []
2. []
3. []
4. Проблема мультиколлинеарности в задачах прогнозирования [1]
5. Квадратичное программирование для выбора признаков [1]