Track 3 · Path · 8 explainers
Neural Networks from Zero
From a single neuron to forward propagation, loss, and backprop
- 1
Neural Networks
Neurons, layers, and how networks learn
- 2
The Perceptron
The simplest neural network — one neuron, one decision boundary
- 3
Forward Propagation
How data flows through a network
- 4
Activation Functions
Why networks need non-linearity to learn
- 5
Bias & Decision Boundaries
How bias terms shift activation and shape decision regions
- 6
Softmax, Logits & Temperature
Turning raw scores into probabilities
- 7
Loss Functions
How networks measure their mistakes
- 8
Backpropagation
How networks learn from their mistakes