We'll use a neural network for classification. In classification, we categorize data, and use the neural network to predict which category each example is in.
You'll learn the theory of classification, including the negative log likelihood loss function, and the sigmoid and softmax activation functions. Then you'll implement a classifier in NumPy that can predict whether a telescope saw a star, galaxy, or quasar.
You can read the full lesson here - github.com/VikParuchuri/zero_... .
And see the previous lessons in this series here - github.com/VikParuchuri/zero_...
Chapters
00:00 - Classification intro
04:15 - Sigmoid activation
08:27 - Binary NLL
14:38 - Binary classification
26:40 - Multiclass encoding
30:05 - Softmax function
35:46 - Multiclass NLL
41:11 - Multiclass classification
This video is part of our new course, Zero to GPT - a guide to building your own GPT model from scratch. By taking this course, you'll learn deep learning skills from the ground up. Even if you're a complete beginner, you can start with the prerequisites we offer at Dataquest to get you started.
If you're dreaming of building deep learning models, this course is for you.
Best of all, you can access the course for free while it's still in beta!
Sign up today!
bit.ly/4016NfK
11 июл 2024
