To evaluate the previously created perceptron, you will use a dataset containing **two input features** and **two distinct classes** (`0` and `1`):

This dataset is **balanced**, with 500 samples from class `1` and 500 samples from class `0`. Therefore, **accuracy** is a sufficient metric for evaluation in this case, which can be calculated using the `accuracy_score()` function:

```python
accuracy_score(y_true, y_pred)
```

`y_true` represents the actual labels, while `y_pred` represents the predicted labels.

The dataset is stored in `perceptron.py` as two **NumPy arrays**: `X` (input features) and `y` (corresponding labels), so they will be simply imported. This file also contains `model`, which is the instance of the `Perceptron` class you previously created. 

Neural networks are powerful algorithms inspired by the structure of the human brain that are used to solve complex machine learning problems. You will build your own Neural Network from scratch to understand how it works. After this course, you will be able to create neural networks for solving classification and regression problems using the scikit-learn library.

First, we will discuss what a neural network is and how it works. And also consider the scope of its application.

Next, we will try to build our own neural network and see how efficiently it copes with learning. We will also consider a ready-made solution from the scikit-learn library.

Finally, we will give you some additional useful information on how to understand which model to use and what types of neural networks there are. To complete the course, you will be tested on your acquired knowledge.

Introduction to Neural Networks

Challenge: Evaluating the Perceptron

Solution

Challenge: Evaluating the Perceptron

Solution