AI & Machine Learning Fundamentals

Learning objectives

• Distinguish AI, machine learning, and deep learning
• Describe supervised and unsupervised learning
• Know when a problem is suitable for ML

AI, ML, and deep learning

Artificial intelligence is the broad field of machines performing tasks that normally require human intelligence. Machine learning is a subset where systems learn patterns from data instead of following hard-coded rules. Deep learning uses multi-layered neural networks and shines on complex data like images and language.

Supervised versus unsupervised

• Supervised learning: the model learns from labeled examples, such as past orders tagged as fraud or not fraud.
• Unsupervised learning: the model finds structure in unlabeled data, such as grouping customers into segments.

Is ML the right tool?

Machine learning is powerful but not always necessary. Ask three questions: do you have enough data? Is the pattern learnable? Is accuracy measurable? If any answer is no, a deterministic rule may serve better.

Key takeaways

• ML learns from data; deep learning is a specialized subset.
• Choose the learning paradigm to match the problem.
• Match the technique to the data and the measurable goal.