MiniTorch Module 0

Welcome to the foundational module of MiniTorch! This assignment introduces you to the core concepts and tools you'll use throughout the course.

Learning Objectives

In this assignment, you will:

• Implement mathematical operators using functional programming principles
• Learn software engineering best practices including testing, debugging, and code organization
• Build neural network infrastructure by creating the foundational components
• Create and visualize classifiers to understand machine learning fundamentals

Getting Started

Prerequisites

Before beginning this assignment, please complete the environment setup:

1. Review the installation guide: Follow the detailed instructions in installation.md to configure your development environment
2. Verify your setup: Ensure all dependencies are properly installed and your environment is working correctly. If you need help ask your TAs.

Assignment Overview

This module provides hands-on experience with the mathematical foundations underlying neural networks. You'll implement core operations that form the building blocks of more complex machine learning systems.

Tasks and Resources

Required Reading

Start by reviewing the module guide:

• Module Overview: https://minitorch.voiremedy.io/module0/module0/

Implementation Tasks

Follow the guides listed in the module documentation to complete each task systematically. Each task builds upon the previous one, so complete them in order.

• Task 0.1: Operators
• Task 0.2: Testing and Debugging
• Task 0.3: Functional Python
• Task 0.4: Modules
• Task 0.5: Visualization

For detailed testing instructions, see testing.md

Task 0.5 Deliverables

Add the required image here along with the parameters that you used.

Visualization

Submission Instructions

1. Commit Your Changes: Make sure all your changes are committed to your repository.
2. Push to GitHub: Push your changes to your GitHub repository.
3. Autograder: Once you have pushed your changes, the autograder will automatically run and provide feedback on your submission. Check the GitHub Actions tab for the results.
4. Resubmit if Necessary: If you need to make changes based on the feedback, make your edits, commit them, and push again. The autograder will re-run with your new changes.

Troubleshooting

If you encounter issues during the submission process, consider the following steps:

• Check the Logs: Review the logs in the GitHub Actions tab for any error messages or warnings.
• Check Instruction in Code: Make sure you followed all instructions in the code comments and documentation.
• Ask for Help: If you're stuck, don't hesitate to reach out to your TAs.

Autograder trigger