https://github.com/vancenceho/50.007-machine-learning

50.005 Machine Learning - Assignments & Project
https://github.com/vancenceho/50.007-machine-learning

kaggle-competition machine-learning machine-learning-algorithms machine-learning-models ml-models python

Last synced: 26 days ago
JSON representation

50.005 Machine Learning - Assignments & Project

• Host: GitHub
• URL: https://github.com/vancenceho/50.007-machine-learning
• Owner: vancenceho
• License: mit
• Created: 2024-06-02T16:45:57.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-08-25T14:43:15.000Z (almost 2 years ago)
• Last Synced: 2025-02-25T09:18:48.677Z (over 1 year ago)
• Topics: kaggle-competition, machine-learning, machine-learning-algorithms, machine-learning-models, ml-models, python
• Language: Jupyter Notebook
• Homepage: https://istd.sutd.edu.sg/undergraduate/courses/50007-machine-learning/
• Size: 5.87 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# 50.007-Machine-Learning

This repository consists of solutions to assignments and links to a project from **50.007 - Machine Learning**, a module took in Summer 2024, from the faculty of **Information Systems Technology & Design** (**ISTD**) at the

_**Singapore University of Technology & Design**_ (**SUTD**).

## Homework

In **Homework 1** (**HW1**) there were two questions which require further implementation of machine learning models and they are listed as followed:

1. Question 2: Linear Classification Implementation (10 marks)

   - Perception Algorithm Implementation (Update Rule)

   - Part (a): Perception Algorithm with 1 epoch

   - Part (b): Perception Algorithm with 5 epoch

   - Part (c): Plotting of decision boundary on test data

   - Part (d): Explanation on possibility of achieving 100% accuracy

2. Question 4: Ridge Regression Implementation (10 marks)

   - Part (a): Ridge Regression Implementation

   - Part (b): Plot of validation & training loss as λ varies on a logrithmic scale

## Project

The project in this module is a team proejct and we were encouraged to form teams in any way we like, consisting of either 4 or 5 people. It is being evaluated as a Kaggle competition, and its summary is as followed:

> Online hate speech is an important issue that breaks the cohesiveness of online social communities and even raises public safety concerns in our societies. Motivated by this rising issue, researchers have developed many traditional machine learning and deep learning methods to detect hate speech on online social platforms automatically.

>

> Essentially, the detection of online hate speech can be formulated as a text classification task: "Given a social media post, classify if the post is hateful or non-hateful". In this project, you are to apply machine learning approaches to perform hate speech classification. Specifically, you will need to perform the following tasks.

It has 4 specific tasks to be completed and are listed as:

1. Task 1: Implement Logistic Regression (10 marks)

2. Task 2: Apply Dimension Reduction Techniques (10 marks)

3. Task 3: Try new machine learning models and race to the top! (25 marks)

4. Task 4: Documenting our journey and thoughts (5 marks)

Our team has applied different machine learning models in our ensemble-based model which we have submitted for **Task 3**.

More information on our project can be found in this repository: [stochastic-gradient-descent](https://github.com/zayne-siew/stochastic-grade-descent)

For more information on the project, please refer to the project scope listed on Kaggle: [50.007 - Machine Learning Course Project](https://www.kaggle.com/competitions/50-007-machine-learning-summer-2024/overview)

## Acknowledgements

These solutions are an undertaking of the [50.007 - Machine Learning](https://istd.sutd.edu.sg/undergraduate/courses/50007-machine-learning/) module during Summer 2024 under the **ISTD** faculty at **SUTD**.

All contents of solutions are credited to:  

Copyright © 2024 _Vancence Ho_ | CSD | SUTD

All contents of the course and project are credited to:  

Copyright © 2024 _Roy Lee_ | ISTD | SUTD  

Copyright © 2024 _Malika Meghjani_ | ISTD | SUTD