О курсе
This course is based on a world-famous book of Introduction to Statistical Learning written by Stanford University's faculty. The text gently and in plain English introduces learners to the world of machine learning. Students gain expertise to solve their own data problems and help attain and measure greater efficiency and automation in the company's and personal data-driven projects.
Most assignments are quizzes with conceptual questions, analytical questions, interpretation of modeling plots, analysis of machine learning algorithms, and some Python coding. Some questions may ask students to evaluate/analyze/solve mathematical formulas, which are behind all machine learning models. Students will also be exposed to Python programming language via machine learning examples in seminars, but are not expected to solve heavy programming or mathematical assignments. Some knowledge of Python is helpful, but not necessary for OOC students. In seminars, practical applications of Python to the problems will be demonstrated. Students will have an opportunity to advance their knowledge using learned models, Google Colab coding environment, and popular packages such as pandas, scikit-learn and TensorFlow
Цели курса
01
Develop an understanding of the process of machine learning from data, which includes exploratory data analysis, visual and analytical understanding interpretation of patterns and guesstimating the appropriate machine learning model
02
Familiarize students with a wide variety of algorithmic and model based methods to extract information from data. This includes a list of linear and non-linear models as well as ensembles of these
03
Teach students to apply and evaluate suitable methods to various datasets by model selection and predictive performance evaluation
Вы научитесь
1. Evaluate and solve a wide array of regression, classification and clustering problems with tools from statistical and machine learning fields using Python programming language
2. Exploratory data analysis in Python
3. Machine learning model training, evaluation, tuning and comparison in Python
4. Data and model visualization in Python
Программа обучения
1. Academic Integrity, Honor, Ethics
2. Review of Calculus, Linear Algebra, Probability, Stats, Python, Colab
3. Introduction to Statistical Learning
4. Linear Regression and K Nearest Neighbor (KNN)
5. Classification: Logistic Regression, Linear Discriminant Analysis, Quadratic Discriminant Analysis, KNN
6. Resampling Methods. Cross Validation (CV), Bootstrap
7. Linear Model Selection and Regularization
8. Non-linear Regression
9. Decision Trees, Bagging, Random Forest, Boosting
10. Support Vector Machines (SVM)
11. Clustering and Dimension Reduction: k-Means, Hierarchical Clustering (HC), DBSCAN, PCA
12. Artificial Neural Networks (ANN) and Introduction to Deep Learning
13. Recurrent Neural Networks (RNN), Long-short Term Memory (LSTM)
14. Convolutional Neural Networks (CNN)
15. Deep Generative Models and Autoencoders
Преподаватели
Приглашенный преподаватель: Факультет компьютерных наук / Департамент больших данных и информационного поиска
Преподаватель: Факультет Компьютерных наук / Департамент больших данных и информационного поиска, Senior Data Scientist в компании 3PM Solutions
Преподаватель: Факультет Компьютерных наук/Департамент больших данных и информационного поиска
Для кого
This course is designed for sufficiently prepared students ready to advance into machine learning for the purpose of self-improvement, career switch or growth into data science or for application of machine learning in the workplace. It is important that the students have a reasonably fresh experience with basic college calculus (specifically, differentiation techniques), linear algebra (operations on matrices), probability and statistics, basic computing coding and a good understanding of English language, since most of the course material will be in English
Документ об окончании
После успешного освоения материалов курса выдается сертификат установленного НИУ ВШЭ образца
Формат обучения
Лекции
via Zoom
Семинары
via Zoom
Консультации
Saturday evenings via Zoom
Промежуточный и итоговый контроль
Auto-generated and auto-graded weekly quizzes
Комментарии
Active participation and video meetings are important in this course and are graded
Стоимость и условия
8 тыс. ₽
Полный доступ к материалам курса + сертификат
Подробнее: публичная оферта
Бесплатно
Только лекции