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
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Deep Learning with TensorFlow and Keras – 3rd edition

You're reading from   Deep Learning with TensorFlow and Keras – 3rd edition Build and deploy supervised, unsupervised, deep, and reinforcement learning models

Arrow left icon
Product type Paperback
Published in Oct 2022
Publisher Packt
ISBN-13 9781803232911
Length 698 pages
Edition 3rd Edition
Tools
Arrow right icon
Authors (3):
Arrow left icon
Sujit Pal Sujit Pal
Author Profile Icon Sujit Pal
Sujit Pal
Antonio Gulli Antonio Gulli
Author Profile Icon Antonio Gulli
Antonio Gulli
Dr. Amita Kapoor Dr. Amita Kapoor
Author Profile Icon Dr. Amita Kapoor
Dr. Amita Kapoor
Arrow right icon
View More author details
Toc

Table of Contents (23) Chapters Close

Preface 1. Neural Network Foundations with TF 2. Regression and Classification FREE CHAPTER 3. Convolutional Neural Networks 4. Word Embeddings 5. Recurrent Neural Networks 6. Transformers 7. Unsupervised Learning 8. Autoencoders 9. Generative Models 10. Self-Supervised Learning 11. Reinforcement Learning 12. Probabilistic TensorFlow 13. An Introduction to AutoML 14. The Math Behind Deep Learning 15. Tensor Processing Unit 16. Other Useful Deep Learning Libraries 17. Graph Neural Networks 18. Machine Learning Best Practices 19. TensorFlow 2 Ecosystem 20. Advanced Convolutional Neural Networks 21. Other Books You May Enjoy
22. Index

Self-organizing maps

Both k-means and PCA can cluster the input data; however, they do not maintain a topological relationship. In this section, we will consider Self-Organizing Maps (SOMs), sometimes known as Kohonen networks or Winner-Take-All Units (WTUs). They maintain the topological relation. SOMs are a very special kind of neural network, inspired by a distinctive feature of the human brain. In our brain, different sensory inputs are represented in a topologically ordered manner. Unlike other neural networks, neurons are not all connected to each other via weights; instead, they influence each other’s learning. The most important aspect of SOM is that neurons represent the learned inputs in a topographic manner. They were proposed by Teuvo Kohonen [7] in 1982.

In SOMs, neurons are usually placed on the nodes of a (1D or 2D) lattice. Higher dimensions are also possible but are rarely used in practice. Each neuron in the lattice is connected to all the input units...

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