University textbook · Computer science
Artificial
Intelligence
From data to language models.
A textbook on how AI systems learn, how to evaluate them and how to use them to study computer science.
First year · Morocco
Second edition
5 chapters
25 sections
25 figures
5 quizzes
Contents
Five chapters, from specifying a problem to evaluating a documentation assistant.
-
Open chapter
From problem to model
Define the inputs, decision and target. Compute a gradient and design a comparison that can fail.
-
Open chapter
Learning and evaluation
Split the data, interpret errors, set a threshold and understand how a network generalizes.
-
Open chapter
Generative model architecture
Follow the computation from tokenizer to decoding. Examine causal attention, post-training and diffusion.
-
Open chapter
Studying and working with LLMs
Set boundaries for tutoring, check an answer against documentation and evaluate retrieval.
-
Open chapter
Reliability and capstone
Audit performance gaps, preserve provenance and compare two assistants on a technical corpus.