This module is a hard requirement for Module 2 and 3.

Course agenda:

1. Basics of linear algebra, computer science, calculus, statistics and probability (day 1).
2. History of AI (day 1).
3. Python basics (day 2).
4. Basics of machine learning (day 2).
   1. Statistical testing;
   2. Data Exploration;
   3. Random forests and Boosting;
   4. Dimensionality reduction techniques;
   5. Function approximation using neural networks.
5. Practical AI concepts (day 3).
   1. Model Training basics:
      1. Loss functions;
      2. Train/Validation/Test Data split;
      3. Training monitoring;
      4. Overfitting & Regularization;
      5. Hyperparameter optimization.
   2. Model Serving: shifts (distributions, pre-processing, etc.).
6. Implementation of simple AI models on various datasets (days 3-4)

Target audience:

Programmers who want to enter the field of AI.

Prerequisites:

1. Basic programming knowledge.
2. Basic knowledge of linear algebra and calculus.

What the student will know after finishing the course:

1. Possess working knowledge about computer science, AI and statistics.
2. Be able to implement and train simple AI models.