https://github.com/sudarshanasrao/ee559-machine_learning-usc

USC graduate level Machine Learning course
https://github.com/sudarshanasrao/ee559-machine_learning-usc

cnn keras machine-learning neural-networks numpy python scikit-learn scipy tensorflow

Last synced: 10 days ago
JSON representation

USC graduate level Machine Learning course

• Host: GitHub
• URL: https://github.com/sudarshanasrao/ee559-machine_learning-usc
• Owner: SudarshanaSRao
• License: mit
• Created: 2023-01-28T04:47:12.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2025-01-02T18:02:42.000Z (21 days ago)
• Last Synced: 2025-01-02T19:19:08.670Z (21 days ago)
• Topics: cnn, keras, machine-learning, neural-networks, numpy, python, scikit-learn, scipy, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 7.52 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.txt

Awesome Lists containing this project

README

        
# EE559--Machine-Learning

Welcome to the repository for my **Machine Learning (EE-559)** assignments! This repository contains all my solutions to the assignments in the course, focusing on classic machine learning algorithms and deep learning using **TensorFlow** and **Keras**. Each assignment demonstrates my ability to implement and apply machine learning models, handle datasets, preprocess data, and evaluate the performance of models using various metrics.

## Key Techniques

1. **Supervised Learning**:

   - Regression (e.g., Linear and Logistic Regression).

   - Classification (e.g., Decision Trees, SVM, KNN).

   

2. **Unsupervised Learning**:

   - Clustering (e.g., K-Means, DBSCAN).

   - Dimensionality Reduction (e.g., PCA).

   

3. **Deep Learning**:

   - Neural Networks using **Keras** and **TensorFlow**.

   - Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs).

   

4. **Model Optimization**:

   - Regularization techniques (L1, L2).

   - Cross-validation, Grid Search, and Random Search for hyperparameter tuning.