# Neural Networks

> ML Prep practice set.

- Stable ID: `neural-networks`
- Area: machine-learning
- Timebox: 55 minutes

Practice forward computation, backpropagation, activation behavior, and parameter counting.

## Instructions

1. Draw the scalar computational graph for backpropagation.

## Ordered items

1. [Forward pass and backpropagation](https://mlprep.iwase.dev/item/original-ml-forward-backprop/?set=neural-networks) — `original-ml-forward-backprop` (medium, 8 min)
2. [Dense-network parameter count](https://mlprep.iwase.dev/item/original-ml-network-params/?set=neural-networks) — `original-ml-network-params` (easy, 4 min)
3. [Neural-network knowledge check](https://mlprep.iwase.dev/item/google-mlcc-neural-network-quiz/?set=neural-networks) — `google-mlcc-neural-network-quiz` (easy, 10 min)
4. [Backpropagation for a multilayer perceptron](https://mlprep.iwase.dev/item/pml-book1-ex13.1/?set=neural-networks) — `pml-book1-ex13.1` (hard, 20 min)

## Completion

Compute one forward and backward pass and count parameters by layer.

## Next recommended practice

- [Convolution](https://mlprep.iwase.dev/set/convolution.md)