人工智慧和機器學習簡介 |青少年人工智慧與Python程式設計夏令營

This introduction to artificial intelligence and machine learning allows learners to start exploring the foundations of these exciting fields. Learners will complete 3 projects using Python code and the same machine learning tools used by professionals in the field. Learners will start learning about the types of machine learning including supervised learning, unsupervised learning, and reinforcement learning. Learners will learn the steps of successful machine learning projects. These steps include data collection, data preparation, model training, accuracy determination, and model improvement. The goal of this class is for students start exploring the foundations of artificial Intelligence and more importantly be excited to continue learning more in the future.

****This is a coding-class using real code and the same tools used by professional AI and Machine Learning engineers. Please, review the coding prerequisites listed at the end of this description or in the parental guidance section.****

Class Syllabus

Day 1
What is Intelligence?
What is AI? 
AI in Our World
What is Machine Learning?
Artificial Intelligence vs. Machine Learning vs. Data Science
Introduction to Google Colab

Day 2
Types of Machine Learning Part 1
Google Colab Introduction
Python NumPy and Pandas Introduction
Machine Learning Project Introduction #1 - Favorite Music Prediction

Day 3
Machine Learning Project  #1 - Favorite Music Prediction
What Problems can AI Solve?
Supervised vs. Unsupervised Learning
Machine Learning Terminology
The Machine Learning Process
Matplotlib Introduction

Day 4
Working with Data in Python
What is Linear Regression
Working with Panda Data Frames
Synthetic Data
Machine Learning Project #2 - Height vs Weight Comparison 

Day 5
Machine Learning Project #2 - Height vs Weight Comparison
Data and AI
Collecting and Preparing Data
Potential problems with AI
Careers in Machine Learning and AI

Day 6
What is Scikit-learn?
Machine Learning Project #3 - Classification: Study Hours Linear Regression
Supervised Learning Algorithm - Linear Regression

Day 7

Supervised Learning Algorithm - Nearest Neighbors
Distance Measurements
Test and Training Data
What is a Confusion Matrix?

Day 8
Iris Data Set
Evaluating Data Sets
Machine Learning Project #4 - Nearest Neighbors
Loss and Determining Accuracy 

Day 9
Machine Learning Project #4 - Neural Networks Handwriting Classification
History of Neural Networks
Weights and Nodes
Review Final Project

Day 10
Machine Learning Project #4 - Neural Networks Handwriting Classification
Loss and Determining Accuracy 
Final Project



****This is a coding-class using real code and the same tools used by professional AI and Machine Learning engineers. Please, review the coding requirements listed at the end of this description or in the parental guidance section.****

Interactive Groups Build the Foundation of Code Skills

Every learner is strongly encouraged to post questions, sample code, and their projects every step of the way. This gives students the chance to learn from each other and start practicing reading code. The instructor will also be providing feedback and guidance regularly throughout the course. 

***Intro to AI and ML Class Prerequisites ****

To succeed in this class, learners should have a strong grasp of coding fundamentals 
including conditional statements, functions, loops, and arrays/lists. Learners should have completed comprehensive multi-week beginner level coding classes before starting this course. Any programming language is fine, such as Python, Java, JavaScript, C / C++, or Swift. There will be a brief review during the first few classes using Python. There are many excellent beginner Python courses available through Outschool.