17 interactive books · English & বাংলা
Don’t just use AI.
Know how it works.
Every model learns the same way: it starts somewhere on a landscape of error and walks downhill, one small step at a time. Our books teach you transformers, deep learning and the maths behind them, with the equation, the code and a picture you can touch.
17 volumes. Pull one off the shelf.
355 chapters and 1835 lessons, from the maths underneath to training models at scale.
Contents
Look inside a real transformer.
This is the model the books build with you: a small GPT with every matrix and every neuron on screen. Step through the forward pass, switch to the neuron view, change the sentence. Nothing here is a video.
Open the lesson it comes fromOne idea, three ways at once.
This is how every lesson is built. Pick a piece of the attention formula and watch the same piece light up in the code and in the picture.
The equation
The code
# one attention headscores = Q @ K.Tscores = scores / math.sqrt(d_k)weights = softmax(scores, dim=-1)out = weights @ V
The picture
Every query is compared with every key: one score per pair of tokens.
Start with one chapter tonight.
Open the free sample chapter. No card needed.