The Mathematics of Large Language Models: A Readable Guide to LLMs, Transformers, Diffusion, Neural Networks, and Generative AI
Kindle Edition or EPUB + Converted PDF نویسندگان: Jason Karpeles
جزئیات
فرمت: Kindle Edition or EPUB + Converted PDF تاریخ انتشار نسخه الکترونیکی : June 5, 2026
؟
لینک: https://www.amazon.com/dp/B0H44K1ZR5
475,000 تومان
زمان تحویل: حداکثر 24 ساعت
توضیحات
Revised and updated for September 2026. Now expanded with 46 original diagrams and explanatory figures, 879 displayed equations, and more than 12k mathematical expressions.Most explanations of artificial intelligence stop just before the mathematics becomesinteresting. This book goes further.Books about AI usually take one of two approaches. They avoid the equations entirely, or theypresent them as if you already speak the language. This one does neither. The mathematics ishere in full, unsimplified, and so is a way to read it.It is written for people who want the actual mathematics behind these systems and who keepgetting stopped by the notation. That is a real and common place to be stuck, and it is not thesame thing as being unable to follow the argument. No advanced degree is assumed. What isassumed is that you are willing to sit with an equation until it opens.How the mathematics is unpackedAfter every equation, two short passages do the work:What It Does explains, in plain language, what the formula is for.Reading the Formula walks through the notation symbol by symbol: what each part contributes,what changes when you alter it, and why the equation is written the way it is.These do not simplify the mathematics. The expression on the page is the one the field uses, atfull strength, because a watered-down version would teach you something that is not true. Whatthe two passages give you is a way to climb up to it.How the book is builtSeventeen chapters and they are not seventeen separate surveys. A preface lays out thestructure before you start: which chapters stand alone, which ones the rest of the book leanson, and several routes through depending on what you came for. Every chapter then opens bysaying what it establishes, what it assumes, and what later chapters build on it. You alwaysknow where you are and why you are there. The storiesEach chapter carries the human story behind the ideas in it: the observation, the failedexperiment, the competition result, the unexpected connection that made researchers rethink howlearning works. The mathematics arrives attached to the problem it was invented to solve, whichis how it was actually discovered and how it is easiest to hold onto.What the book coversApproximation and what a network can represent. Optimization and what training can actuallyfind. Generalization, implicit bias, and double descent. Symmetry and convolution. Recurrenceand state-space models. Attention and transformers. Graphs. Latent-variable and adversarialmodels. Diffusion and optimal transport. Continuous-depth models. Operator learning forscientific problems. Bayesian methods and calibrated uncertainty. Robustness and causality.Scaling laws and in-context learning. And a closing chapter on hallucination: what themathematics says about what a model cannot know, and when abstaining is the correct answer.One honest note on fitIf you already read this notation fluently, the explanatory apparatus will be in your way. Youare welcome here, and you should skip it: the results, derivations and citations stand withoutit. But the scaffolding is the point of this book, and it was built for readers who need it.If you have ever wanted to move past surface-level explanations and understand the mathematicsthat makes modern AI work, this book was written for you.Jason Karpeles is an award winning data scientist and predictive-analytics innovator with thirty yearsbuilding forecasting and machine-learning models in industry. Jason earned a Masters Degree in Economics from NYU and an MBA from Duke University. Full biography under Aboutthe Author.
475,000 تومان
زمان تحویل: حداکثر 24 ساعت