Quick Start Guide

Quick Start Guide#

From Zero to Building Neural Networks

Complete setup + first module in 15 minutes

Purpose: Get hands-on experience building ML systems in 15 minutes. Complete setup verification and build your first neural network component from scratch.

2-Minute Setup#

Let’s get you ready to build ML systems:

Step 1: One-Command Setup

# Clone repository
git clone https://github.com/mlsysbook/TinyTorch.git
cd TinyTorch

# Automated setup (handles everything!)
./setup-environment.sh

# Activate environment
source activate.sh

What this does:

  • Creates optimized virtual environment (arm64 on Apple Silicon)

  • Installs all dependencies (NumPy, Jupyter, Rich, PyTorch for validation)

  • Configures TinyTorch in development mode

  • Verifies installation

See Essential Commands for detailed workflow and troubleshooting.

Step 2: Verify Setup

# Run system diagnostics
tito system doctor

You should see all green checkmarks. This confirms your environment is ready for hands-on ML systems building.

See Essential Commands for verification commands and troubleshooting.

15-Minute First Module Walkthrough#

Let’s build your first neural network component following the TinyTorch workflow:

        graph TD
    Start[Clone & Setup] --> Edit[Edit Module<br/>tensor_dev.ipynb]
    Edit --> Export[Export to Package<br/>tito module complete 01]
    Export --> Test[Test Import<br/>from tinytorch import Tensor]
    Test --> Next[Continue to Module 02]

    style Start fill:#e3f2fd
    style Edit fill:#fffbeb
    style Export fill:#f0fdf4
    style Test fill:#fef3c7
    style Next fill:#f3e5f5

See Student Workflow for the complete development cycle.

Module 01: Tensor Foundations#

Learning Goal: Build N-dimensional arrays - the foundation of all neural networks

Time: 15 minutes

Action: Start with Module 01 to build tensor operations from scratch.

# Step 1: Edit the module source
cd modules/01_tensor
jupyter lab tensor_dev.ipynb

You’ll implement core tensor operations:

  • N-dimensional array creation

  • Basic mathematical operations (add, multiply, matmul)

  • Shape manipulation (reshape, transpose)

  • Memory layout understanding

Key Implementation: Build the Tensor class that forms the foundation of all neural networks

# Step 2: Export to package when ready
tito module complete 01

This makes your implementation importable: from tinytorch import Tensor

See Student Workflow for the complete edit → export → validate cycle.

Achievement Unlocked: Foundation capability - “Can I create and manipulate the building blocks of ML?”

Next Step: Module 02 - Activations#

Learning Goal: Add nonlinearity - the key to neural network intelligence

Time: 10 minutes

Action: Continue with Module 02 to add activation functions.

# Step 1: Edit the module
cd modules/02_activations
jupyter lab activations_dev.ipynb

You’ll implement essential activation functions:

  • ReLU (Rectified Linear Unit) - the workhorse of deep learning

  • Softmax - for probability distributions

  • Understand gradient flow and numerical stability

  • Learn why nonlinearity enables learning

Key Implementation: Build activation functions that allow neural networks to learn complex patterns

# Step 2: Export when ready
tito module complete 02

See Student Workflow for the complete edit → export → validate cycle.

Achievement Unlocked: Intelligence capability - “Can I add nonlinearity to enable learning?”

Track Your Progress#

After completing your first modules:

Check your new capabilities: Use the optional checkpoint system to track your progress:

tito checkpoint status  # View your completion tracking

This is helpful for self-assessment but not required for the core workflow.

See Student Workflow for the essential edit → export → validate cycle.

Validate with Historical Milestones#

After exporting your modules, prove what you’ve built by running milestone scripts:

After Module 07: Build Rosenblatt’s 1957 Perceptron - the first trainable neural network
After Module 07: Solve the 1969 XOR Crisis with multi-layer networks
After Module 08: Achieve 95%+ accuracy on MNIST with 1986 backpropagation
After Module 09: Hit 75%+ on CIFAR-10 with 1998 CNNs
After Module 13: Generate text with 2017 Transformers
After Module 18: Optimize for production with 2018 Torch Olympics

See Journey Through ML History for complete timeline, requirements, and expected results.

The Workflow: Edit modules → Export with tito module complete N → Run milestone scripts to validate

See Student Workflow for the complete cycle.

What You Just Accomplished#

In 15 minutes, you’ve:

Setup Complete

Installed TinyTorch and verified your environment

Created Foundation

Implemented core tensor operations from scratch

First Capability

Earned your first ML systems capability checkpoint

Your Next Steps#

Immediate Next Actions (Choose One):#

Continue Building (Recommended): Begin Module 03 to add layers to your network.

Master the Workflow:

For Instructors:

Pro Tips for Continued Success#

The TinyTorch Development Cycle:

  1. Edit module sources in modules/NN_name/ (e.g., modules/01_tensor/tensor_dev.ipynb)

  2. Export with tito module complete N

  3. Validate by running milestone scripts

See Student Workflow for detailed workflow guide and best practices.

You’re Now a TinyTorch Builder#

Ready to Build Production ML Systems

You've proven you can build ML components from scratch. Time to keep going!

Continue Building → Master Commands →

What makes TinyTorch different: You’re not just learning about neural networks—you’re building them from fundamental mathematical operations. Every line of code you write builds toward complete ML systems mastery.

Next milestone: After Module 08, you’ll train real neural networks on actual datasets using 100% your own code!

Contents