README.md

Neural_Network Tasks

Task 1 (Perceptron Classification Model)

Description:

Implement the Perceptron learning algorithm on a single layer neural networks which can be able to classify a stream of input data to one of a set of predefined classes.

Task 2 (Adaline Classification Model)

Description:

Implement the Adaline learning algorithm using MSE on a single layer neural networks which can be able to classify a stream of input data to one of a set of predefined classes.

• Iris Data Include 3 Classes setosa, versicolor, virginica and 4 Features X1, X2, X3, X4

1- training

• Use the iris data in both your training and testing processes. (Each class has 50 samples: train NN with 30 non-repeated samples randomly selected, and test it with the remaining 20 samples)

2- Testing

• Test the classifier with the remaining 20 samples of each selected classes and find confusion matrix and compute overall accuracy.

3- Plotting

• Draw all possible combinations of features like (X1, X2), (X1, X3), (X1, X4), (X2, X3), (X2, X4), and (X3, X4)
• Draw a line that can discriminate between the two learned classes.
• Draw Learned Classes
• Draw Confusion Matrix

Task Screenshots

Task Working Screenshots

1. Data Visualization According to Feature 2, 4

---

2. App Overview

---

3. Traingin Result Visualization

---

4. Testing Result Visualization

---

5. Confusion Matrix

---

6. Overall Accuracy

---

7. In Case Adding Bias or Change the Classes or Features

• Testing Result Visualisation

• Confusion Matrix

• Overall Accuracy

---

References

• Tkinter GUI
• Perceptron Overview
• Matplot Library
• Panadas & Dataframe