The three terms are related like Russian dolls: deep learning is a type of machine learning, and machine learning is a way of building artificial intelligence.
Artificial intelligence (AI)
AI is the broad goal of making computers do tasks that normally need human intelligence: understanding language, recognising images, planning or making decisions. Early AI systems were often hand-written rules.
Machine learning (ML)
Machine learning is a way of building AI by learning from data instead of writing every rule by hand. Show a model thousands of past transactions labelled 'fraud' or 'not fraud', and it learns the patterns itself.
- Supervised learning: learning from labelled examples, as with spam filters or price prediction.
- Unsupervised learning: finding structure in unlabelled data, such as customer segments.
- Reinforcement learning: learning by trial and reward, as in game-playing agents and robotics.
Deep learning
Deep learning uses neural networks with many layers. It powers modern speech recognition, computer vision and large language models. It usually needs more data and computing power, but it handles messy inputs such as images, audio and free text very well.
Which should you learn first?
Begin with core machine learning: data handling, regression, classification and model evaluation. Deep learning and generative AI build directly on those foundations.