Artificial Intelligence
Checking your access…
Module 1What is AI & Machine Learning
L1What is Artificial Intelligence?
L2What is Machine Learning?
L3Types of Machine Learning
L4Real-world Applications of AI
L5A Brief History of AI
Module 2Mathematics for AI
L1Vectors and Matrices
L2The Dot Product and Matrix Multiplication
L3Statistics Essentials I — Mean, Variance, Standard Deviation
L4Statistics Essentials II — Probability
L5Gradients and the Idea of a Derivative
Module 3Python for AI
L1Python Quick Start
L2NumPy Arrays
L3pandas DataFrames
L4scikit-learn Basics — the Estimator API
L5Your First End-to-End Pipeline
Module 4Machine Learning Concepts
L1Supervised vs Unsupervised Learning (in depth)
L2Features, Labels and Data
L3Train/Test Split and Validation
L4Overfitting and Underfitting
L5Evaluation Metrics
Module 5Neural Networks Basics
L1The Artificial Neuron (Perceptron)
L2Layers and Activation Functions
L3How Learning Happens — Loss and Gradient Descent
L4Backpropagation Intuition
L5Network Architectures
Module 6Practical ML with a Library
L1The scikit-learn Workflow
L2Classification with k-Nearest Neighbours
L3Logistic Regression and Decision Trees
L4Improving Models — Preprocessing and Pipelines
L5Building a Complete Classifier (the Iris Project)
Module 7AI Ethics, Limitations & Fairness
L1Bias in AI
L2Privacy and Data
L3Fairness, Accountability and Transparency
L4Limitations of AI
L5Responsible AI in Practice
Module 8Capstone: Build an AI Project
L1Scoping an ML Project
L2From Data to Model — The Pipeline
L3Evaluating and Improving
L4Presenting Your Project
L5Capstone Walkthrough — the Flower Classifier