A 195-page primer traces one mathematical thread through every major generative AI model
The Little Book of Generative AI Foundations: An Intuitive Mathematical Primer
Tianhua Chen's revised preprint builds a single, derivation-driven path from PCA and variational autoencoders through diffusion models, normalising flows, autoregressive factorisations, GANs, Wasserstein GANs, and energy-based models. Rather than cataloguing architectures, it shows how these families are derived and related, keeping the mathematics intact while making the structure of generative modelling easier to grasp. The 195-page version adds visual explanations throughout and is aimed at mathematically curious researchers, practitioners, and students.
The aim is to make the structure of generative modelling more accessible without removing the mathematical substance needed to understand how these models are derived and related.
- nh23423fefe
I don't like:
> Changing coordinates. Given a vector x expressed in the standard basis, we change coordinates by applying
x_eig = V^−1 x.
> This operation does not change the vector itself; it only changes how the vector is represented, converting it into eigenvector coordinates.
I'm sure the author knows about the difference between the vector and a coordinate vector given a basis. I just don't like this wording. It's weird to say applying a function doesn't affect a change.
- hasteg
Another book which I would highly recommend for learning the math (or at least getting a very good idea of how it works) behind machine learning/transformers is "Why Machines Learn: The Elegant Math Behind Modern AI" by Anil Ananthaswamy. I read it this past year and I found it was extremely good at pacing and building up intuition to the "how and why" of most important math concepts and discoveries in ML that have lead to where we are today. For those who don't already have a fairly deep understanding of linear algebra, statistics, and multivariate calculus, this book will be a far more gentle introduction yet still has enough rigor for you to come away with something.
- p1esk
Wow, this book is surprisingly readable! I like how he starts from basics of linear algebra.
- prideout
My favorite little book is François Fleuret's: The Little Book of Deep Learning
- nblgbg
Are there any deep learning books with some problems to solve ?