Bangkit ML Materials 2024

Materials, Source Code and Implementations for Bangkit 2024 Machine Learning

Introduction

Welcome to the Bangkit 2024 Machine Learning repository. This repository contains all the materials, source code, and implementations for the Bangkit 2024 Machine Learning course. The course is designed to provide a comprehensive understanding of machine learning concepts, algorithms, and practical applications.

Structure

The repository is organized into several modules, each focusing on different aspects of machine learning. Below is an overview of the key modules:

ILT3 - Supervised Learning

This module covers the concepts and applications of supervised learning. It includes hands-on exercises with classification and regression models using Python and popular machine learning libraries.

• Notebooks:
  • ILT_3_Hands_on_Classification_Model.ipynb: Demonstrates various classification algorithms and model evaluation techniques.
  • ILT_3_Hands_on_Regression_Model.ipynb: Focuses on regression models, including data preprocessing, model training, and evaluation.

ILT4 - Unsupervised Learning and ANN

This module covers the concepts and applications of unsupervised learning and artificial neural networks (ANN). It includes hands-on exercises with clustering algorithms and building ANN models.

• Notebooks:

  • Clustering_Lab_ILT_4.ipynb: Demonstrates various clustering algorithms, including K-Means, Agglomerative Clustering, DBSCAN, and more.
  • ann_sample.ipynb: Focuses on building a simple artificial neural network (ANN) using TensorFlow and Keras.

• Scripts:

  • system_recommendation.py: A modular script for building a recommendation system using TF-IDF and cosine similarity.
  • ann_sample.py: A modular script for building a simple artificial neural network (ANN) based on the ann_sample.ipynb notebook.

ILT6 - Deploying Models

This module covers the concepts and applications of deploying machine learning models. It includes hands-on exercises with various deployment tools and frameworks.

• Notebooks:

  • Deploying_Models_Lab_ILT_6.ipynb: Demonstrates different methods and tools for deploying machine learning models.

• Projects:

  • TF.js: Deploying models in the browser using TensorFlow.js.
  • TFLite: Deploying models on mobile and edge devices using TensorFlow Lite.
  • TFServe: Serving models in production using TensorFlow Serving.
  • TF Datasets: Utilizing TensorFlow Datasets for efficient data loading and preprocessing.

Running the Notebooks

You can run the notebooks using Jupyter Notebook or Google Colab. To open the notebooks in Google Colab, click the "Open in Colab" badge at the top of each notebook.

License

This project is licensed under the MIT License. See the LICENSE file for more details.