Concept
Deep learning
Machine learning with many-layered neural networks.
What should you learn before Deep learning?
- Feature engineeringTurning raw data into inputs a model can learn from: scaling, encoding and new features.
- Machine learningBuilding systems that learn patterns from data instead of following hand-written rules.
- Optimization and gradient descentAdjusting model parameters step by step to reduce a loss.
- Supervised learningLearning from labelled examples to predict a label or value.
- Neural networksLayers of weighted connections trained by backpropagation to learn patterns.
What to learn after Deep learning
- TransformersThe attention-based neural network architecture behind modern language models.
Connections to other concepts
- Part of
- Machine learning
Practise Deep learning
- Advanced Machine Learning Interview Questions8 questions on Deep learning