From inputs to network outputs

Understand the idea

A network combines weighted inputs, activations and learned layers. Hidden width counts units within a layer; a tuple describes successive hidden layers. Task-specific outputs come after the shared representation.

Understand layers, units and task-shaped outputs.Scroll the diagram horizontally if needed.

What the syntax does

MLPClassifier(hidden_layer_sizes=(24,), max_iter=500, random_state=42): Creates a neural network model.
random_state: 42, None
max_iter: 100, 500, 1000
hidden_layer_sizes: (24,), (16, 8)
The one-item tuple (24,) means one layer of 24 units; (16, 8) means two layers. max_iter caps optimisation. alpha is a nonnegative weight penalty; convergence and validation evidence both matter.
Classification and regression share architecture notation but use different outputs and metrics.
model.get_params()['hidden_layer_sizes']: Reads the architecture setting without fitting a network.
hidden_layer_sizes: (24,), (16, 8)

Outputs you create

answer: The requested result, with the values, labels and row order described by this task.

LINE24 · first 8 rows
`distance`	`duration`
1	5.30501
1.47826	11.2361
1.95652	11.8488
2.43478	14.809
2.91304	10.7589
3.3913	19.4972
3.86957	17.89
4.34783	15.531

Your task

Create an unfitted MLPClassifier named model with one hidden layer of 24 units.
Store its hidden_layer_sizes setting in answer.

answer

Hints

Think: Use a one-item tuple and keyword arguments to describe a neural-network architecture.

Tools: Use (24,), MLPClassifier, model.get_params()['hidden_layer_sizes']. Read the visible syntax meanings before editing.

Approach: Create an unfitted MLPClassifier named model with one hidden layer of 24 units. Store its hidden_layer_sizes setting in answer. Keep the supplied row order and inspect the named output after running.

Explained solution

from sklearn.neural_network import MLPClassifier
model = MLPClassifier(hidden_layer_sizes=(24,), max_iter=500, random_state=42)
answer = model.get_params()['hidden_layer_sizes']

The tuple (24,) means one hidden layer, not 24 layers. Constructing the estimator does not train weights or produce predictions. Regression uses MLPRegressor but shares this architecture notation.