Skip to content

High School Foundations of Machine Learning

Suggested Prerequisites

Artificial Intelligence in the World, Applications of Artificial Intelligence, Procedural Programming

Description

Believe it or not, machine learning has become a large part of every interaction we have with technology. In this course, you will deepen your understanding of machine learning (ML) practices and applications. You will discover the mathematical foundation needed to create algorithms for use in artificial intelligence and machine learning. You will also explore the essential knowledge and skills related to computer coding and software development. The learning activities sprinkled throughout the course will give you the opportunity to write and test different machine learning models. By the end of this course, you will have a foundational understanding of machine learning and the exciting career opportunities available in the field of artificial intelligence.

Module One: Trained for Success

-Real-world machine learning

-Abstraction

-Using Google Colaboratory

-Constructing graphs to represent data

-Symbolic, numeric, and feature vector representations

-Tree traversal and searching algorithms

-Representation and reasoning

-Humans vs. machine learning


Module Two: Pursuit of Knowledge

-Supervised learning

-Classification and regression

-Root mean squared error (RMSE)

-Unsupervised learning

-Clustering algorithms

-Decision trees

-Reinforcement learning

-Neural networks

-Backpropagation

-Stochastic gradient descent


Module Three: Trending Data

-Machine learning statistics

-Real-world datasets

-Neural networks functions

-Linear regression and time-series values

-KNN and Naïve Bayes algorithms

-Reasoning problems that ML can solve

-Bias in ML

-Cross-validation sets

-Sources of data

-Creating and adjusting a chatbot

Module Four: Crafty Calculations

-Size of data significance

-Organizing and manipulating data

-APIs, RSSs, and web scraping using Python

-Finding data patterns

-Using Pandas to train a model

-Data visualizations to tell a story

-Garbage in, garbage out

-Model complexity and transparency


Module Five: Modeling Intelligence

-Problems ML can solve

-Data preparation

-Decision trees

-Random and Isolation Forest algorithms

-Cross-validation sets

-Anomaly detection

-Computer vision tasks and natural language processing

-AI tools

-GPUs, TPUs, FPGAs


Module Six: Evaluating Solutions

-Human-in-the-loop approach

-Proxies

-Human vs. AI fairness

-Types of bias in AI

-Goals and acceptable behaviors of AI

-Evaluating and updating models

-SQL and NoSQL databases

-Jobs impacted by AI

-Security and privacy risks

-AI accountability