logo

ITechResearch

Machine learning

595 000 ₸
Allocated 2 Quotas

Form an understanding of the basic principles of learning with and without a teacher.Be able to apply machine learning algorithms in practical applications such as robot design (perception, control), text analysis (online search, anti-spam), computer vision, medical information systems, audio processing, database mining, and other areas.Learn to apply ensemble methods, stacking, bagging, and bousting. Be able to utilize best practices for model training, generating additional data, monitoring and pipelining ML development, and Kaggle competitions.

Special condition

In order to participate in the IT school, a guarantee fee of 50,000 tenge is required. The guarantee fee is mandatory and is not refundable in case of non-fulfillment of the student's obligations to the educational process: such as skipping classes, non-compliance with the academic schedule, late completion of assignments or other violations. Upon successful completion of the course, the guarantee fee is refunded.

Course details

level

For all

Study format

Online

Start

September

Entrance exams

No

Duration, in weeks

28

Duration in academic hours

112

Education language

Kazakh

Classes days_of_week

Mon-Fri

Teaching methodology

There are more practices than theories

Qualifications

Junior (Strong) machine learning specialist

Classes format

Lessons are conducted online 2 times a week for 2 hours each.

Skills


Interpret machine learning tasks, the basic principles of learning with/without a teacher. Extracting data from various sources (reading from files, API, database)

Compare classification tasks and regression tasks. To illustrate classification tasks (binary and multiple). Compare the most well-known classifiers (logistic regression, decision trees, random forest, support vector machine).

Apply different types of classifiers to solve practical problems. Explain the need for cross-validation.

Interpret the clustering task. To put into practice the basic clustering algorithms (k-means and hierarchical methods) and the principal component method (PCA). Data visualization using Pandas, Matplotlib.

Feature Engineering: evaluation of the significance of features, feature selection, dimensionality reduction methods.

Interpret the types of neural networks (convolutional, recurrent, deep), the possibility of changing network parameters (number of layers, number of neurons). Apply neural networks to solve practical problems.

FAQ

Similar courses

Other courses from ITechResearch