monktensor

monktensor

The Learning Course

6 units | 23 lessons

Build a deep learning framework from scratch.

You'll build the engine that powers PyTorch and TensorFlow, automatic differentiation, and train a neural network with it. This course teaches the ideas, not the implementation: by the end you'll understand every part well enough to write the framework yourself.

The loop every framework runs, over and over

Data
inputs
Forward
prediction
Loss
how wrong
Backward
gradients
Update
better weights

Forward to a prediction, measure the error, send gradients backward, nudge the weights. Repeat until it learns.

What you need before starting

A little programming

You can read and write basic Python: variables, functions, loops, classes.

High-school algebra

Functions, graphs, slopes. That's the floor.

Calculus

Not required upfront. Derivatives and the chain rule are taught from zero in Unit 0.

What you'll understand by the end

The engine
A computation graph
that records every operation
and computes its own gradients
The network
Neurons, layers, an MLP
built on top of the engine
with a clean parameter API
The training
A loss, gradient descent,
and a loop that teaches the net
to separate two classes

This course teaches the concepts. You write the framework, that's where the understanding sticks.