# Neural Networks Practice

> ML preparation set.

- Stable ID: `neural-networks-practice`
- Area: machine-learning
- Kind: practice
- Timebox: 35 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/machine-learning/neural-networks/original-ml-forward-backprop/) — `original-ml-forward-backprop` (8 min)
2. [Dense-network parameter count](https://mlprep.iwase.dev/machine-learning/neural-networks/original-ml-network-params/) — `original-ml-network-params` (4 min)
3. [Neural-network knowledge check](https://mlprep.iwase.dev/machine-learning/neural-networks/google-mlcc-neural-network-quiz/) — `google-mlcc-neural-network-quiz` (10 min)

## Completion

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