Notes by Lex Toumbourou

Notes from the Deep Learning for Coders (2020) video series by Jeremy Howard and Sylvain Gugger (fast.ai)

Matrix multiplication is a mathematical operation between 2 matrices that returns a matrix.

For each row in the first matrix, take the Dot Productf …

An operation between 2 vectors that returns a number.

Binary Cross-Entropy (BCE), also known as log loss, is a loss function used in binary or multi-label machine learning training.

It's nearly identical to Negative …

Pre-sizing is a technique for preparing images for training a neural network.

In standard image pipelines, images are resized to a size suitable for our …

Categorical Cross-Entropy Loss Function, also known as Softmax Loss, is a loss function used in multiclass classification model training. It applies the Softmax Function to …

Cross-entropy measures the average number of bits required to identify an event if you had a coding scheme optimised for one probability distribution $q …$

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 …

a multi-class classification loss 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 …