Concept
Neural networks
Layers of weighted connections trained by backpropagation to learn patterns.
Neural networks
Then learnDeep learning
What should you learn before Neural networks?
- 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 descentNetworks learn by gradient descent.
- Supervised learningLearning from labelled examples to predict a label or value.
What to learn after Neural networks
- Deep learningMachine learning with many-layered neural networks.
Connections to other concepts
- Used by
- PyTorch