Review

This part is a review of the Perceptron. It aims to refresh your memory of what you have learned in class.

• Perceptron
• Artificial Neural Network (ANN)
• Response and Activation function
• Weight update
• Stopping rules

Please download the review notebook by right-clicking the link. Then select "Save link as..." to save the file to your local disk. Next, upload it to your own Google Drive and open it using using Google Colab. You should see the following if you open the notebook successfully.

Introduction

Classifying underwater objects can be difficult for humans as our senses (like seeing, touching, hearing) are restricted. Thus utilizing tools to help us conduct that is important.

The dataset we will use for this lab is the Sonar dataset from the Machine Learning Repository of UCI. We will get the response signals from the sonar detector of different objects.

https://archive.ics.uci.edu/ml/datasets/Connectionist+Bench+(Sonar,+Mines+vs.+Rocks)

We will classify the underwater objects into "rock" and "metal" using perceptron.

Lab Work

A couple of lab tasks are given to you to practice your skills in processing data and to build a perceptron classification model.

Please download the lab tasks notebook and the dataset to be used by right-clicking the link. Then, select "Save link as..." to save the files to your local disk. Next, upload them to your own Google Drive (the same folder of the lab review notebook) and open it using Google Colab. You should see the following if you open the notebook successfully.

Submission & Grading

This is an odd-numbered lab, so there is no need to submit anything. Have fun playing with the notebooks! ;)

Frequently Asked Questions

• UPDATES on lab5_task.ipynb (Please download the latest version):
  - Updated the description and task definition for task1, task2.2, and task 2.3
  - Added examples for difference between numpy.dot() and numpy.matmul()
  - Added demo of sklearn implementation for the lab tasks
  
  

This list is incomplete; you can help by expanding it.