Beginner · 8 articles · MODULE 1: FOUNDATIONS
Tutorial · Beginner · 24 min
This is the refresher everything else stands on. A probability is a proportion between 0 and 1, and a risk is exactly that — events divided by everyone.
Includes Colab notebook
By: Anacodic Team
Start Reading →Tutorial · Beginner · 22 min
An exponent builds a number up by repeated multiplication (10^3 = 1000); a logarithm is its exact inverse — it asks "what power gives me this number?" (log10(1000) =…
Includes Colab notebook
By: Anacodic Team
Start Reading →Tutorial · Beginner · 17 min
A weighted average lets some numbers "count more" than others.
By: Anacodic Team
Start Reading →Tutorial · Beginner · 16 min
When a single choice must serve a whole group, you combine each person's satisfaction into one score and pick the highest-scoring option.
By: Anacodic Team
Start Reading →Tutorial · Beginner · 15 min
Once you split something among people — bandwidth, budget, or satisfaction with a shared choice — you need a number for how fairly it was split.
By: Anacodic Team
Start Reading →Tutorial · Beginner · 15 min
When several parts cooperate to produce one result, the Shapley value fairly attributes credit by averaging each part's marginal contribution over every order it could join.
By: Anacodic Team
Start Reading →Tutorial · Beginner · 20 min
Entropy, surprisal and perplexity explain what a language model's loss number means. Confidence and correctness are different axes.
By: Anacodic Team
Start Reading →Tutorial · Beginner · 22 min
Almost every number a model produces comes out of one operation: matrix multiplication. Shapes are the debugging, and cost is n times k times m.
By: Anacodic Team
Start Reading →