| Publisher | Packt Publishing; 2nd ed. edition (September 29, 2023) |
| Language | English |
| Paperback | 538 pages |
| ISBN-10 | 1803247762 |
| ISBN-13 | 978-1803247762 |
| Item Weight | 2.05 pounds |
| Dimensions | 9.25 x 7.52 x 1.11 inches |
| Best Sellers Rank | #61,730 in Books (See Top 100 in Books) #6 in Software Design Tools #23 in Natural Language Processing (Books) #34 in Python Programming |
| Customer Reviews | 4.3 out of 5 stars 67Reviews |
While many algorithm books cover traditional and foundational topics, I’ve tried to keep this book modern by diving into state-of-the-art algorithms in areas like deep learning, Large Language Models (LLMs), and sequential models. I want to show that the world of algorithms, is not static, but always evolving, which I also think is a more comprehensive view of algorithms.
An important topic I’d want to bring up about this is bias and explainability. In today's world, where AI ethics is crucial, I’ve wanted this book to stand out in addressing the all-important topic of recognizing hidden biases in data and ensuring the transparency and explainability of algorithms.
(Image: Deep and wide LLM architecture models)
This second edition of 50 Algorithms Every Programmer Should Know not only has the updated versions of most algorithms from the first edition in line with current IT trends, but it also aims to help readers delve into advanced deep learning architectures and new chapters on sequential models like LSTMs, GRUs, RNNs, and LLMs.
Furthermore, through this edition, I've tried to shed light on contemporary topics such as addressing hidden data biases and demystifying algorithm explainability.
I've designed this book to strike a balance between helping readers select and use an algorithm to solve a real-world problem and explaining the logic behind it for a deeper understanding.
For example, it begins with an introduction to algorithms, allowing readers to understand the various algorithm design techniques. As readers progress, they explore more advanced concepts and are taught the practical application of these algorithms using real-world examples.
(Image: A fundamental algorithm design)
I’ve had a rich background in cloud computing, AI, and machine learning that I want to bring to the table with this book. I’ve had experience in high-profile projects with the Canadian Federal Government, taught at Google, and am a visiting professor at Carleton University. My experience in all of these different projects with their own focuses and challenges has taught me some insights that I’d like to share, whether it’s about the applicability of some algorithms, or maybe their ethics, or their future direction. I hope it also adds a unique perspective to what I’ve written.
