Foundations
The concepts everything else builds on: what separates a program from a model, and what's behind probabilities, vectors, hardware and neural networks.
- Program, Algorithm, Model Compared
- Input and Output: How a Function "Thinks"
- Tokenizers: How Text Breaks into Tokens
- Token IDs: What a Number Means
- Scalar, Vector, Matrix, Tensor: The Building Blocks of the Numbers
- Probability and Softmax: How a Model Decides
- Parameters, Training and Use: How a Model Learns
- Model Size and Hardware: Where a Model Fits
- The Artificial Neuron: How a Sum Becomes an Output