Cross-Entropy
Cross-entropy measures the average number of bits required to identify an event if you had a coding scheme optimised for one probability distribution
Articles in the permanent category
-
-
Information Entropy
Entropy is a measure of uncertainty of a random variable's possible outcomes.
It's highest when there are many equally likely outcomes. As you introduce more …
-
-
Softmax Function
The Softmax Activation Function converts a vector of numbers into a vector of probabilities that sum to 1. It's applied to a model's outputs (or …
-
Sigmoid Function
The Sigmoid function, also known as the Logistic Function, squeezes numbers into a probability-like range between 0 and 1.1 Used in Binary Classification model …
-
-
Server Authoritative Multiplayer
A typical multiplayer game architecture where the server has authority over the game state. The server keeps track of players' positions, the resources they own …
-
Out-of-Domain
When data is provided to a model that is significantly different from what it was trained on, it's referred to as out-of-domain data.
-
-
Fleeting Notes
Fleeting notes in Zettelkasten are for capturing ideas while reading, listening, or thinking. They are designed to be short-lived and should be stored in an …
