Applied Machine Learning Basics

The goal of this course is to introduce Machine Learning and give you experience using one common ML function, image classification. Becoming familiar with one method gives you an advantage when encountering new procedures, enlarging your pool of marketable skills. You will train and build a classification model, then deploy your code on a website, Raspberry Pi, or your phone. After taking this course you should feel ready to take more advanced AI and Machine Learning courses. Having constructed one actual product, you will be better able to apply new knowledge in practical settings. Chapter 1: Introduction to Machine Learning A brief overview of the field of Machine Learning (ML) in the context of Artificial Intelligence. Chapter 2: Data for Machine Learning An introduction to datasets, how to find pre-made sets or create your own. Chapter 3: Artificial Neural Networks An introduction to artificial neural networks used in image classification. Chapter 4: Convolutional Neural Networks A more detailed look at how neural networks work and how to refine them to get better results. Chapter 5: Development Now that you have experience creating predictive models with supervised learning, we deploy a sample model on a web page or smartphone.

Chapter 1: Introduction to Machine Learning A brief overview of the field of Machine Learning (ML) in the context of Artificial Intelligence. • Define Machine Learning. • Describe what kinds of problems ML can solve. • Differentiate the 3 main approaches to Machine Learning. Chapter 2: Data for Machine Learning An introduction to datasets, how to find pre-made sets or create your own. • Define several kinds of datasets. • Describe the process of creating an image dataset. • Upload and run a Google Colab Notebook. Chapter 3: Artificial Neural Networks An introduction to artificial neural networks used in image classification. • Set up model training and testing code procedures. • Interpret training data to improve learning. Chapter 4: Convolutional Neural Networks A more detailed look at how neural networks work and how to refine them to get better results. • Set up model training and testing code procedures. • Interpret training data to improve learning. Chapter 5: Development Now that you have experience creating predictive models with supervised learning, we deploy a sample model on a web page or smartphone. • Give options for deploying a model once it has been trained and tested. • Describe why you might need to convert a model to a different framework. • Modify a smartphone app to deploy your machine learning model.

All required reference materials are provided with this program. Technical requirements: Internet Connection • Broadband or High-Speed (DSL, Cable, Wireless) Hardware Requirements • Processor - 2GHz Processor or Higher • Memory - 1 GB RAM Minimum Recommended Software Requirements • Operating Systems - Windows 7, 8 or 10; Mac OS x 10 or higher • Microsoft Office 2007, 2010 or 2013 or a Word Processing application to save and open Microsoft Office formats (.doc, .docx, .xls, .xlsx, .ppt, .pptx) • Internet Browsers - Google Chrome is highly recommended • Cookies MUST be enabled • Pop-ups MUST be allowed (Pop-up Blocker disabled) • Adobe PDF Reader

This class is an independent-study course. Students will have all the resources needed to successfully complete the course within the online material. A student helpdesk is available for technical support during the course enrollment.