learn deep. ship safe.Practice testsFollow ByteMunSubscribe

Concept

Deep learning

Machine learning with many-layered neural networks.

Concept map
Learn firstNeural networks
Part of Machine learningDeep learning
Then learnTransformers

What should you learn before Deep learning?

  1. Feature engineeringTurning raw data into inputs a model can learn from: scaling, encoding and new features.
  2. Machine learningBuilding systems that learn patterns from data instead of following hand-written rules.
  3. Optimization and gradient descentAdjusting model parameters step by step to reduce a loss.
  4. Supervised learningLearning from labelled examples to predict a label or value.
  5. 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

Practise Deep learning

All topics