This training is organized by BITM. Training will be held in BITM.

Course Outline:

1. Introduction to machine learning, Basic ideas about A.I, Machine learning for A.I, other approaches towards A.I
2. Python basics, overview
3. Regression analysis (theory and practical)  
4. Regression analysis with practical data project
5. Data pre-processing intro, Dealing with missing data
6. Data types, class distribution, class imbalance  
7. Standardizing data, why and when to standardize, scaling (theory and practical)
8. Standardizing data project with practical data.
Project 1
9. Classification basics using Artificial neural network (theory)
10. Classification basics using Artificial neural network(practical)
11. Feature selection and analysis, PCA, Dimension reduction (theory)
12. Feature selection and analysis, PCA, Dimension reduction (practical 1)
13. Feature selection and analysis, PCA, Dimension reduction (practical 2)
14.. Getting data for training, scraping 1
15. Scraping 2
16. Dealing with Database 1
17. Dealing with database 2
18. More with classification (theory and practical)
Project 2
19. Dealing with Image in ANN (theory and practical)
20. Intro to CNN, idea and math, why and when CNN
21. Using CNN for Image classification  1
22. Using CNN for Image classification 2
Project 3
23. Multiclass classification with CNN Theory
24. Multiclass classification with CNN Practical

Curriculum