MIT - Machine Learning with Python: From Linear Models to Deep Learning

This repository contains my personal projects and homework assignments for the edX course Machine Learning with Python: From Linear Models to Deep Learning, offered by the Massachusetts Institute of Technology (MIT).

About This Repository

The main purpose of this repository is to document my journey through the world of machine learning. It serves as a personal portfolio of my work, showcasing the concepts I've learned and the skills I've developed throughout the course. All the code, notebooks, and solutions are my own.

---

Course Information

• Course Title: Machine Learning with Python: From Linear Models to Deep Learning
• Institution: Massachusetts Institute of Technology (MIT)
• Platform: edX

Topics Covered

• Introduction to Machine Learning
• Linear Regression and Regularization
• Logistic Regression and Classification Models
• Support Vector Machines (SVM)
• Decision Trees and Ensemble Methods
• Unsupervised Learning (e.g., Clustering)
• Neural Networks and Backpropagation
• Deep Learning for Computer Vision (CNNs)
• Deep Learning for Sequential Data (RNNs)
• Model Evaluation and Hyperparameter Tuning

---

Repository Structure

.
├── linear_classifiers
│   └── HomeWork1.ipynb
├── neural_networks_lectures
│   ├── lecture8.ipynb
│   └── .ipynb_checkpoints
│       └── lecture8-checkpoint.ipynb
├── project_1_sentiment_analysis
│   ├── 200.txt
│   ├── 4000.txt
│   ├── main.py
│   ├── project1.py
│   ├── reviews_submit.tsv
│   ├── reviews_test.tsv
│   ├── reviews_train.tsv
│   ├── reviews_val.tsv
│   ├── stopwords.txt
│   ├── test.py
│   ├── toy_data.tsv
│   └── utils.py
└── project_2_digit_recognition
    ├── ._.DS_Store
    ├── .DS_Store
    ├── utils.py
    ├── utils.py.bak
    ├── __pycache__
    │   ├── utils.cpython-311.pyc
    │   └── utils.cpython-313.pyc
    ├── Datasets
    │   ├── mnist.pkl.gz
    │   ├── test_labels_mini.txt.gz
    │   ├── test_multi_digit_mini.pkl.gz
    │   ├── train_labels_mini.txt.gz
    │   └── train_multi_digit_mini.pkl.gz
    ├── part1
    │   ├── cubic_features_checker.py
    │   ├── features.py
    │   ├── kernel_softmax.ipynb
    │   ├── kernel.py
    │   ├── linear_regression.py
    │   ├── main.py
    │   ├── README.md
    │   ├── softmax.py
    │   ├── svm.py
    │   ├── test.py
    │   ├── theta.pkl.gz
    │   ├── __pycache__
    │   │   ├── features.cpython-311.pyc
    │   │   ├── features.cpython-313.pyc
    │   │   ├── kernel.cpython-311.pyc
    │   │   ├── kernel.cpython-313.pyc
    │   │   ├── linear_regression.cpython-311.pyc
    │   │   ├── linear_regression.cpython-313.pyc
    │   │   ├── softmax.cpython-311.pyc
    │   │   ├── softmax.cpython-313.pyc
    │   │   ├── svm.cpython-311.pyc
    │   │   └── svm.cpython-313.pyc
    │   └── .ipynb_checkpoints
    │       └── kernel_softmax-checkpoint.ipynb
    ├── part2-mnist
    │   ├── nnet_cnn.py
    │   ├── nnet_fc.py
    │   └── train_utils.py
    ├── part2-nn
    │   └── neural_nets.py
    └── part2-twodigit
        ├── ._.DS_Store
        ├── .DS_Store
        ├── conv.py
        ├── mlp.py
        ├── train_utils.py
        ├── utils_multiMNIST.py
        └── sample_images

---

Technologies Used

This course and its projects are primarily based on Python and its rich ecosystem of data science libraries.

• Language: Python 3.x
• Libraries:
  • NumPy - For numerical operations.
  • Pandas - For data manipulation and analysis.
  • Matplotlib & Seaborn - For data visualization.
  • Scikit-learn - For building and evaluating classical machine learning models.
  • TensorFlow or PyTorch - For developing deep learning models.
  • Jupyter Notebook - For interactive coding and analysis.

---

Disclaimer

The solutions and code provided in this repository are for my personal educational purposes only. They represent my own understanding and effort in completing the assignments. If you are currently enrolled in this course, please adhere to the institution's academic integrity policies and use this repository only as a reference.

---