Scribd
Upload
2 views2 pages

Course AI Python

The document outlines a 6-month AI and Python training program divided into three phases: Python Intermediate to Advanced, Classical Machine Learning, and Deep Learning. Each phase includes weekly topics and checkpoints to assess progress, with a strong emphasis on practical coding and exercises. Recommended resources for further learning are also provided.

Uploaded by

petrosyan.narek2010
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views2 pages

Course AI Python

The document outlines a 6-month AI and Python training program divided into three phases: Python Intermediate to Advanced, Classical Machine Learning, and Deep Learning. Each phase includes weekly topics and checkpoints to assess progress, with a strong emphasis on practical coding and exercises. Recommended resources for further learning are also provided.

Uploaded by

petrosyan.narek2010
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

AI & Python

AI Theory + Coding | 6 Months

Phase 1 — Python Intermediate → Advanced Weeks 1–6

Week 1 ■ OOP — classes, inheritance, polymorphism

Week 2 ■ Decorators, Generators, Context Managers

Week 3 ■ NumPy — array ops, broadcasting, indexing

Week 4 ■ Pandas — DataFrame, groupby, merge, cleaning

Week 5 ■ Matplotlib + Seaborn — visualization

Week 6 ■ CHECKPOINT — mini data analysis project

Phase 2 — Classical Machine Learning Weeks 7–14

Week 7 ■ Linear / Logistic Regression — theory + sklearn

Week 8 ■ Decision Trees + Random Forest

Week 9 ■ SVM + KNN

Week 10 ■ Feature Engineering + Preprocessing

Week 11 ■ Model Evaluation — CV, metrics, confusion matrix

Week 12 ■ XGBoost + LightGBM

Week 13 ■ Unsupervised — KMeans, PCA, DBSCAN

Week 14 ■ CHECKPOINT — Kaggle beginner competition

Phase 3 — Deep Learning Weeks 15–24

Week 15 ■ Neural Networks — forward / backprop theory

Week 16 ■ PyTorch basics — tensors, autograd

Week 17 ■ CNN — image classification

Week 18 ■ RNN + LSTM — sequence data

Week 19 ■ Transformer — attention mechanism theory

Week 20 ■ Hugging Face — pretrained models

Week 21 ■ NLP pipeline — tokenization, embeddings


Week 22 ■ Computer Vision project

Week 23 ■ NLP project

Week 24 ■ CHECKPOINT — end-to-end AI project

Weekly Schedule

■ Mon / Thu — AI / Python (1 hr each)

■ Code every day — even 20 min

■ After each topic: solve 2 exercises

■ Weekly: write a short summary note

Recommended Resources
• [Link] — Practical Deep Learning for Coders
• Andrej Karpathy — Neural Networks: Zero to Hero (YouTube)
• Kaggle Learn — free micro-courses
• Hands-On ML with Scikit-Learn & TensorFlow (book)
• Papers With Code — latest research

Progress Rule: tick each checkbox only after completing theory + exercise + hard problem.

You might also like