🧠Understand Neural Network Fundamentals
Strip neural networks back to arithmetic — weighted sums, a squash function, and stacking. By the end you'll trace a forward pass with a pencil and design a tabular-problem architecture you can defend choice by choice.
Phase 1A Neuron Is Just Arithmetic
See a neuron as arithmetic, not biology
A neuron is a weighted sum and a squash, nothing more
6 minA neuron is a weighted sum and a squash, nothing more
One layer draws lines; two layers draw shapes
6 minOne layer draws lines; two layers draw shapes
The squash is what makes the whole thing work
6 minThe squash is what makes the whole thing work
A network is a stack of weighted sums separated by squashes
7 minA network is a stack of weighted sums separated by squashes
Phase 2Forward Pass by Hand
Run a forward pass on a 2-3-1 net by hand
Lay out the 2-3-1 network as numbers, not boxes
6 minLay out the 2-3-1 network as numbers, not boxes
Compute z, apply ReLU, write down h
7 minCompute z, apply ReLU, write down h
One last weighted sum gives you the prediction
6 minOne last weighted sum gives you the prediction
The loss is one number that says how wrong you are
6 minThe loss is one number that says how wrong you are
Backpropagation is the chain rule with a spreadsheet
7 minBackpropagation is the chain rule with a spreadsheet
Phase 3Activations, Depth, and Width
Pick activations, depth, and width with reasons
You inherited a model with sigmoid hidden layers and slow training
7 minYou inherited a model with sigmoid hidden layers and slow training
Same parameter budget — go wider or deeper?
7 minSame parameter budget — go wider or deeper?
Your friend says any neural net can learn any function
7 minYour friend says any neural net can learn any function
Three teammates, three opinions on hidden layer width
7 minThree teammates, three opinions on hidden layer width
Phase 4Design a Tabular Architecture
Design and defend a tabular-problem architecture
Draw the architecture for a real tabular problem and defend it
12 minDraw the architecture for a real tabular problem and defend it
Frequently asked questions
- What is a neuron in a neural network, really?
- This is covered in the “Understand Neural Network Fundamentals” learning path. Start with daily 5-minute micro-lessons that build from fundamentals to hands-on application.
- Why do neural networks need activation functions?
- This is covered in the “Understand Neural Network Fundamentals” learning path. Start with daily 5-minute micro-lessons that build from fundamentals to hands-on application.
- What's the difference between depth and width in a neural network?
- This is covered in the “Understand Neural Network Fundamentals” learning path. Start with daily 5-minute micro-lessons that build from fundamentals to hands-on application.
- How does backpropagation actually update the weights?
- This is covered in the “Understand Neural Network Fundamentals” learning path. Start with daily 5-minute micro-lessons that build from fundamentals to hands-on application.
- How do I choose an architecture for a tabular dataset?
- This is covered in the “Understand Neural Network Fundamentals” learning path. Start with daily 5-minute micro-lessons that build from fundamentals to hands-on application.
Related paths
🐍Python Decorators Introduction
Build one mental model for Python decorators that covers closures, argument passing, functools.wraps, and stacking — then ship a working caching or logging decorator from scratch in under 30 lines.
🦀Rust Lifetimes Explained
Stop reading `'a` as line noise and start reading it as scope arithmetic — one failing snippet at a time — until you can thread lifetimes through a small parser or iterator adapter without fighting the borrow checker.
☸️Kubernetes Core Concepts
Stop drowning in 30+ resource types. Build the mental model one primitive at a time -- pods, deployments, services, ingress, config -- then deploy a real app with rolling updates and health checks.
📈Big O Intuition
Stop treating Big O as math you memorized for an interview — build the intuition to spot O(n²) disasters, pick the right data structure without thinking, and rewrite a slow function from O(n²) to O(n) in under five minutes.