1. Define a loss function that quantifies our unhappiness with the scores across the training data

2. Come up with a way of efficiently finding the parameters that minimize the loss function(optimization)

Loss Functions

• Suppose : 3 training examples, 3 classes.

  With some W the scores $f(x, W) = Wx$ are:

  

• A loss function tells how good our current classifier is

Given a dataset of examples $\{(x_i, y_i)\}_{i=1}^N$ where $x_i$ is image and $y_i$ is (integer) label

Loss over the dataset is an average of loss over examples:

$$ ⁍ $$

Multiclass SVM loss

❗ SVM에 대해서 공부하기❗

⇒ 추가 예정

Given an example $(x_i, y_i)$ where $x_i$ is image and $y_i$ is (integer) label

and using the shorthand for the scores vector $s = f(x_i, W)$

the SVM loss has the form:

$$ ⁍ $$