Loss Functions & Task Design

Easy

The choice of loss function defines what your model optimizes. MSE, cross-entropy, hinge loss, and contrastive losses each encode different assumptions.

Learning Objectives

→Derive binary cross-entropy from MLE
→Implement categorical cross-entropy
→Understand triplet and contrastive losses
→Choose loss function given task type

Coding Problems (5)

Categorical Cross-Entropy

Pro

~15 min· Medium

Huber Loss

Pro

~15 min· Medium

Binary Cross-Entropy Loss

Pro

~12 min· Easy

KL Divergence

Pro

~12 min· Easy

Softmax Cross-Entropy from Logits

~18 min· Medium

Concept Check

Optional multiple-choice questions on the ideas behind this section. Most useful after you have tried the coding problems above.