- Preface
- Notation and Conventions
- Part I: Foundations
- Sequence Modelling and the Two Paradigms
- Mathematical Preliminaries
- The Sequential Paradigm: Recurrent Networks
- Learning in Recurrent Networks: Backpropagation Through Time
- Gated Recurrence: LSTM and GRU
- Part II: The Parallel Paradigm
- Attention: From Alignment to Self-Attention
- The Transformer Architecture
- Positional Encoding: Recovering Order Without Recurrence
- Training the Parallel Model
- Part III: Comparative Analysis
- Computation, Parallelism, and Complexity
- Expressivity, Memory, and Long-Range Dependencies
- Hardware, Systems, and Throughput
- Empirical Comparison and Scaling Behaviour
- Part IV: Synthesis and Outlook
- Hybrids and Successors: The Return of Recurrence
- Choosing an Architecture: A Decision Framework
- Synthesis, Case Studies, and Outlook
- Back Matter
- Appendix A: Key Derivations
- Glossary of Key Terms
- References
- About This Book
- About the Author
The Sequence Machines: Comparing RNN and Transformer Architectures in Modern AI
Two architectures. One choice: process a sequence step by step, or all at once. From that single decision flows almost every difference between RNNs and Transformers: how fast they train, how far they remember, and why parallelism won. A rigorous, diagram-rich comparison that derives the field instead of just surveying it.
Minimum price
$19.00
$29.00
You pay
Author earns
About
About the Book
The Sequence Machines is a graduate-level comparison of the two neural network architectures that have defined modern AI: recurrent neural networks (RNNs) and Transformers. It is built around a single thesis, that almost every practical difference between them follows from one design choice, whether information moves through a sequence step by step or all at once. Rather than survey the field, the book derives it, building both architectures from first principles and showing exactly where and why each one breaks. (The full multi-paragraph version and the "What's inside" list from my earlier message read the same, just with commas in place of the dashes.)
Author
About the Author
Louis Chukwunonye Nwadike is a researcher and writer working at the intersection of machine learning, applied statistics, and the engineering of large-scale systems. His interests include the mathematical foundations of deep learning, distributed training systems, and neural sequence architectures, along with the broader question of how complex algorithms can be explained clearly to a non-specialist audience. He has taught and advised in multiple settings on neural network theory and practice for several years.
He has a personal commitment to making rigorous machine learning literature accessible, especially to students from regions where access to expensive textbooks and elite seminar rooms is not the default. When he is not writing or working with code, he reads outside his field on purpose, in the belief that ideas travel between disciplines more easily than people often expect.
Contents
Table of Contents
Get the free Community Edition
You can get the free Community Edition in PDF or EPUB just by sharing your name and email address with the author, or you can just click this link to read a shorter sample online...
The Leanpub 60 Day 100% Happiness Guarantee
Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.
See full terms...
Earn $8 on a $10 Purchase, and $16 on a $20 Purchase
We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.
(Yes, some authors have already earned much more than that on Leanpub.)
In fact, authors have earned over $15 million writing, publishing and selling on Leanpub.
Learn more about writing on Leanpub
Free Updates. DRM Free.
If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).
Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.
Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.
Learn more about Leanpub's ebook formats and where to read them
Write and Publish on Leanpub
You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses!
Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks.
Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. (Or, if you are producing your ebook your own way, you can even upload your own PDF and/or EPUB files and then publish with one click!) It really is that easy.