Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Hands-On Meta Learning with Python

You're reading from   Hands-On Meta Learning with Python Meta learning using one-shot learning, MAML, Reptile, and Meta-SGD with TensorFlow

Arrow left icon
Product type Paperback
Published in Dec 2018
Publisher Packt
ISBN-13 9781789534207
Length 226 pages
Edition 1st Edition
Languages
Arrow right icon
Author (1):
Arrow left icon
Sudharsan Ravichandiran Sudharsan Ravichandiran
Author Profile Icon Sudharsan Ravichandiran
Sudharsan Ravichandiran
Arrow right icon
View More author details
Toc

Table of Contents (12) Chapters Close

Preface 1. Introduction to Meta Learning 2. Face and Audio Recognition Using Siamese Networks FREE CHAPTER 3. Prototypical Networks and Their Variants 4. Relation and Matching Networks Using TensorFlow 5. Memory-Augmented Neural Networks 6. MAML and Its Variants 7. Meta-SGD and Reptile 8. Gradient Agreement as an Optimization Objective 9. Recent Advancements and Next Steps 10. Assessments 11. Other Books You May Enjoy

Chapter 6: MAML and Its Variants

  1. MAML is one of the recently introduced and most commonly used meta learning algorithms, and it has lead to a major breakthrough in meta learning research. The basic idea of MAML is to find better initial parameters so that, with good initial parameters, the model can learn quickly on new tasks with fewer gradient steps.
  2. MAML is model agnostic, meaning that we can apply MAML for any models that are trainable with gradient descent.
  3. ADML is a variant of MAML that makes use of both clean and adversarial samples to find the better and robust initial model parameter, θ. 
  4. In FGSM, we get the adversarial sample of our image and we calculate the gradients of our loss with respect to our image, more clearly input pixels of our image instead of the model parameter.
  5. The context parameter is a task-specific parameter...
lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime
Banner background image