Track 2 · Path · 6 explainers
How Models Learn
Prediction tasks, loss functions, gradient descent, and the knobs that drive training
- 1
Classification vs Regression
Two kinds of prediction and when to use each
- 2
Loss Functions
How networks measure their mistakes
- 3
Gradient Descent
Optimizing by following the slope downhill
- 4
Feature Scaling
Why and how to normalize features for faster convergence
- 5
Hyperparameters
The knobs you tune before training begins
- 6
Epochs & Batching
How data is fed to the model in epochs, batches, and shuffles