Sebastian Raschka
@sebastianraschka·88.6K subscribers·307 videos
L8.4 Logits and Cross Entropy
Posted
February 23, 2021
Views
11,834
Likes
177
Comments
3
Engagement
1.52%
February 23, 2021
11,834
177
3
1.52%
Every word spoken in this episode is indexed. Type any phrase to jump straight to the moment it was said.
Type any word or phrase that may have been spoken. Click a result to seek the player to that exact moment.
Try a name, a topic, or a quoted line
6:48Now PlayingSebastian's books
In the context of deep learning, you will often stumble upon terms such as "logits" and "cross entropy". As we will see in this video, these are not new concepts but are something that we can derive from our understanding of logistic regression. In fact, the logits are what we are already computing in logistic regression. And the cross entropy is essentially equivalent to the logistic regression loss function -- you can think of it as just another name.
-------
This video is part of my Introduction of Deep Learning course.
The complete playlist
A handy overview page with links to the materials
-------
If you want to be notified about future videos, please consider subscribing to my channel
Sentinel Indexing in Progress
Metadata and chapters are available. Claim extraction for this episode is pending.
All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel provides research tools that promote discovery and accountability across political media.
