You're reading from 50 Algorithms Every Programmer Should Know Tackle computer science challenges with classic to modern algorithms in machine learning, software design, data systems, and cryptography

Product type Paperback

Published in Sep 2023

Publisher Packt

ISBN-13 9781803247762

Length 538 pages

Edition 2nd Edition

Languages

Processing

Tools

Processing

Concepts

Data Structures and Algorithms

Author (1):

Imran Ahmad

View More author details

Table of Contents (22) Chapters

Preface

1. Section 1: Fundamentals and Core Algorithms FREE CHAPTER

2. Overview of Algorithms

3. Data Structures Used in Algorithms

4. Sorting and Searching Algorithms

5. Designing Algorithms

6. Graph Algorithms

7. Section 2: Machine Learning Algorithms

8. Unsupervised Machine Learning Algorithms

9. Traditional Supervised Learning Algorithms

10. Neural Network Algorithms

11. Algorithms for Natural Language Processing

12. Understanding Sequential Models

13. Advanced Sequential Modeling Algorithms

14. Section 3: Advanced Topics

15. Recommendation Engines

16. Algorithmic Strategies for Data Handling

17. Cryptography

18. Large-Scale Algorithms

19. Practical Considerations

20. Other Books You May Enjoy

21. Index

Introducing RNNs

RNNs, are a special breed of neural networks designed specifically for sequential data. Here’s a breakdown of their key attributes.

The term “recurrent” stems from the unique feedback loop RNNs possess. Unlike traditional neural networks, which are essentially stateless and produce outputs solely based on the current inputs, RNNs carry forward a “state” from one step in the sequence to the next.

When we talk about a “run” in the context of RNNs, we’re referring to a single pass or processing of an element in the sequence. So, as the RNN processes each element, or each “run,” it retains some information from the previous steps.

The magic of RNNs lies in their ability to maintain a memory of previous runs or steps. They achieve this by incorporating an additional input, which is essentially the state or memory from the previous run. This mechanism allows RNNs to recognize and learn the...