Cross Entropy Loss
Type: Concept
As of November 2026, Cross Entropy Loss has been mentioned in 3 episodes across 2 podcasts, first heard Jan 2026 on Carnegie Mellon University Deep Learning. Cross entropy loss is a fundamental concept discussed as a key loss function for classification problems in machine learning.
In information theory, the cross-entropy between two probability distributions and , over the same underlying set of events, measures the average number of bits needed to identify an event drawn from the set when the coding scheme used for the set is optimized for an estimated probability distribution , rather than the true distribution .
| Mentioned in | 3 episodes on 2 podcasts (as of November 2026) |
|---|---|
| First heard | Jan 2026 on Carnegie Mellon University Deep Learning |
| Field | Machine Learning |
What do podcasts say about Cross Entropy Loss?
3 quotes, recorded on Carnegie Mellon University Deep Learning and Kaggle.
The goal of cross entropy loss is therefore to encourage high probability for the crack clause.
Carnegie Mellon University Deep Learning · · Hear itYou're going to implement two loss functions.
Carnegie Mellon University Deep Learning · · Hear itI used cross entropy instead of more common losses.
Kaggle · · Hear it
How do different shows talk about Cross Entropy Loss?
2 shows discussed Cross Entropy Loss in these episodes.
- Carnegie Mellon University Deep Learning — 2 episodes; stays neutral
You're going to implement two loss functions.
11785 Spring 2026 - Homework 1 Bootcamp - Kaggle — 1 episode
I used cross entropy instead of more common losses.
Kaggle Winners Walkthroughs: BirdCLEF 2025 with Team Nikita Babych
Who talks about Cross Entropy Loss on podcasts?
Cross Entropy Loss came up; the most recent mention was Jan 2026 on Kaggle.