Search icon CANCEL
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
The Handbook of NLP with Gensim

You're reading from   The Handbook of NLP with Gensim Leverage topic modeling to uncover hidden patterns, themes, and valuable insights within textual data

Arrow left icon
Product type Paperback
Published in Oct 2023
Publisher Packt
ISBN-13 9781803244945
Length 310 pages
Edition 1st Edition
Arrow right icon
Author (1):
Arrow left icon
Chris Kuo Chris Kuo
Author Profile Icon Chris Kuo
Chris Kuo
Arrow right icon
View More author details
Toc

Table of Contents (24) Chapters Close

Preface 1. Part 1: NLP Basics
2. Chapter 1: Introduction to NLP FREE CHAPTER 3. Chapter 2: Text Representation 4. Chapter 3: Text Wrangling and Preprocessing 5. Part 2: Latent Semantic Analysis/Latent Semantic Indexing
6. Chapter 4: Latent Semantic Analysis with scikit-learn 7. Chapter 5: Cosine Similarity 8. Chapter 6: Latent Semantic Indexing with Gensim 9. Part 3: Word2Vec and Doc2Vec
10. Chapter 7: Using Word2Vec 11. Chapter 8: Doc2Vec with Gensim 12. Part 4: Topic Modeling with Latent Dirichlet Allocation
13. Chapter 9: Understanding Discrete Distributions 14. Chapter 10: Latent Dirichlet Allocation 15. Chapter 11: LDA Modeling 16. Chapter 12: LDA Visualization 17. Chapter 13: The Ensemble LDA for Model Stability 18. Part 5: Comparison and Applications
19. Chapter 14: LDA and BERTopic 20. Chapter 15: Real-World Use Cases 21. Assessments 22. Index 23. Other Books You May Enjoy

How cosine similarity is used in images

Any digital images can be converted into vectors. The vectors can be compared in the latent vector space by the cosine similarity score to indicate the “resemblance” of two images. Figure 5.2 first shows the digital image of the number 5 as a 2D matrix.

Figure 5.2 – The image of “5” (image from [1])

Figure 5.2 – The image of “5” (image from [1])

This 2D matrix can be converted by a neural network such as a Convolutional Neural Network (CNN) to become vectors. The square boxes in Figure 5.2 represent a series of layers, including convolutional, pooling, and fully connected layers, to convert an image to a long vector. Let me describe the process a little bit. Initially, the CNN applies multiple convolutional layers to extract hierarchical features from the image. These layers detect patterns such as edges, textures, and shapes. As the network progresses through convolution and pooling layers, it captures increasingly complex...

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