Computer Science › Section L · Artificial intelligence › Topic L.5
Artificial neural networks
Instead of following instructions written step by step, an artificial neural network learns its behaviour from examples by adjusting thousands, or billions, of numerical weights. This topic builds one neuron at a time, shows what a single neuron cannot do, and explains how networks are trained.
In this topic
- Inspired by the brain
- An artificial neuron
- Worked example: computing a neuron's outputs
- Neurons as logic gates
- Layers of neurons
- Worked example: a network for XOR
- Training instead of programming
- Worked example: training a neuron to compute OR
- Smooth neurons and backpropagation
- Deep learning: power and limits
- Common mistakes to avoid
- Key takeaways
This topic is part of Wuanberri Pro. Checking your access…