https://github.com/ansinitro/programming-for-ai
AITU Master Degree course Programming for AI | Instructuor: Arailym Tleubayeva
https://github.com/ansinitro/programming-for-ai
Last synced: 7 days ago
JSON representation
AITU Master Degree course Programming for AI | Instructuor: Arailym Tleubayeva
- Host: GitHub
- URL: https://github.com/ansinitro/programming-for-ai
- Owner: ansinitro
- Created: 2025-10-23T03:06:44.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-11-16T02:56:22.000Z (8 months ago)
- Last Synced: 2025-11-16T04:29:48.613Z (8 months ago)
- Language: Jupyter Notebook
- Size: 7.69 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Programming for Artificial Intelligence
## 🎯 Course Overview
**Programming for AI** provides a foundation in programming principles, tools, and frameworks essential for developing Artificial Intelligence (AI) applications.
Students will learn to design, implement, and test AI-related programs using **Python**, **NumPy**, **Pandas**, **Scikit-learn**, **PyTorch**, and **TensorFlow**.
This course bridges theory and practice — helping students gain both algorithmic understanding and hands-on experience in working with real-world datasets, building machine learning models, and managing AI development workflows.
---
## 🧠 Learning Objectives
By completing this course, you will learn to:
- Use key tools for AI development — Python, Git/GitHub, Jupyter/Colab, and cloud environments.
- Create and manipulate data structures, apply OOP principles, and write modular, reusable code.
- Read and write datasets in formats like CSV, JSON, and TXT, including working with APIs and large data files.
- Apply **NumPy** and **tensor operations** for mathematical tasks such as linear algebra and random sampling.
- Load, clean, and preprocess datasets for machine learning experiments.
- Apply **text preprocessing** and **NLP techniques** (tokenization, TF-IDF, embeddings).
- Visualize data and models using **Matplotlib**, **Seaborn**, and **TensorBoard**.
- Implement machine learning models (classification, regression, clustering) using **Scikit-learn**.
- Design and train **neural networks** (MLP, CNN) using **PyTorch** or **TensorFlow**.
---
## 📚 Topics Covered
### Week 1–5: Python Foundations and Data Handling
- Python syntax, data types, OOP concepts
- File handling (CSV, JSON, large data)
- NumPy and tensor operations
- Dataset management and preprocessing
### Week 6–7: NLP and Visualization
- Basics of natural language processing (tokenization, sentiment analysis)
- Visualization of data and model performance
### Week 8–9: Machine Learning & Neural Networks
- Supervised and unsupervised ML models
- Neural network fundamentals, activation functions, and training
### Week 10: Mini Project
- Design and implementation of an AI mini project using learned concepts
---
## ⚙️ Tools & Technologies
- **Languages:** Python
- **Libraries:** NumPy, Pandas, Scikit-learn, PyTorch, TensorFlow
- **Visualization:** Matplotlib, Seaborn, TensorBoard
- **Development:** Jupyter Notebook, Google Colab, Git/GitHub
- **Cloud Platforms:** Kaggle, Google Cloud, AWS (optional)
---
## 🧩 Practical Components
Students will complete:
- **4 programming assignments** (covering Python, NumPy, ML, and Neural Networks)
- **1 midterm and 1 endterm exam**
- **Final mini project** — an applied AI system built on a real dataset
---
## 📈 Evaluation Scheme
| Component | Weight | Description |
|------------|---------|-------------|
| Attestation I | 30% | Assignments + Midterm |
| Attestation II | 30% | Assignments + Endterm |
| Final Project | 40% | Project + Presentation |
Grading follows a percentage-based scale:
- **A (95–100):** Excellent
- **B (80–89):** Good
- **C (65–79):** Satisfactory
- **D (50–64):** Minimal pass
- **F (<50):** Fail
---
## 🧠 Skills You’ll Gain
- Python development for AI applications
- Data preprocessing and feature engineering
- Tensor manipulation and matrix operations
- Model design and evaluation
- Data visualization and performance tracking
- Neural network training and debugging
- Version control and collaboration with GitHub
---
## 📘 Recommended Learning Resources
- *Head First Python* — Paul Barry (O’Reilly, 2023)
- *Python Crash Course* — Eric Matthes (No Starch Press, 2019)
- *Python for Everybody* — Dr. Charles Severance
- *Statistical Learning with Sparsity* — Trevor Hastie et al.
- *Data Science for Business* — Foster Provost & Tom Fawcett
---
## 🧾 Example Mini Project Ideas
- Sentiment analysis of product reviews
- Image classifier using CNN
- Chatbot using NLP and text embeddings
- Predictive model for customer behavior
- AI-powered data visualization dashboard
---
## 🧩 Course Keywords
`Python` · `AI Programming` · `Machine Learning` · `Data Science` · `Deep Learning` · `NumPy` · `PyTorch` · `TensorFlow` · `OOP` · `Data Visualization`
---
## 📂 Structure Example
```
Programming-for-AI/
├── assignments/
│ ├── assignment_1_python_basics.ipynb
│ ├── assignment_2_numpy_tensors.ipynb
│ ├── assignment_3_ml_models.ipynb
│ └── assignment_4_neural_networks.ipynb
├── data/
│ ├── sample_dataset.csv
├── mini_project/
│ ├── report.md
│ └── presentation.pptx
└── README.md
```
---
## 🚀 Outcome
After completing this course, you will be able to independently develop, test, and optimize AI models — from data preprocessing to deployment — using professional programming and machine learning tools.