Book Image

50 Algorithms Every Programmer Should Know - Second Edition

By : Imran Ahmad
4 (5)
Book Image

50 Algorithms Every Programmer Should Know - Second Edition

4 (5)
By: Imran Ahmad

Overview of this book

The ability to use algorithms to solve real-world problems is a must-have skill for any developer or programmer. This book will help you not only to develop the skills to select and use an algorithm to tackle problems in the real world but also to understand how it works. You'll start with an introduction to algorithms and discover various algorithm design techniques, before exploring how to implement different types of algorithms, with the help of practical examples. As you advance, you'll learn about linear programming, page ranking, and graphs, and will then work with machine learning algorithms to understand the math and logic behind them. Case studies will show you how to apply these algorithms optimally before you focus on deep learning algorithms and learn about different types of deep learning models along with their practical use. You will also learn about modern sequential models and their variants, algorithms, methodologies, and architectures that are used to implement Large Language Models (LLMs) such as ChatGPT. Finally, you'll become well versed in techniques that enable parallel processing, giving you the ability to use these algorithms for compute-intensive tasks. By the end of this programming book, you'll have become adept at solving real-world computational problems by using a wide range of algorithms.
Table of Contents (22 chapters)
Free Chapter
1
Section 1: Fundamentals and Core Algorithms
7
Section 2: Machine Learning Algorithms
14
Section 3: Advanced Topics
20
Other Books You May Enjoy
21
Index

Summary

In this chapter we discussed advanced sequential models, which are advanced techniques designed to process input sequences, especially when the length of output sequences may differ from that of the input. Autoencoders, a type of neural network architecture, are particularly adept at compressing data. They work by encoding input data into a smaller representation and then decoding it back to resemble the original input. This process can be useful in tasks like image denoising, where noise from an image is filtered out to produce a clearer version.

Another influential model is the Seq2Seq model. It’s designed to handle tasks where input and output sequences have varying lengths, making it ideal for applications like machine translation. However, traditional Seq2Seq models face the information bottleneck challenge, wherein the entire context of an input sequence needs to be captured in a single, fixed-size representation. Addressing this, the attention mechanism was...