Questions sur l’IA, expliquées clairement
Des explications simples sur l’intelligence artificielle, l’apprentissage automatique, les réseaux de neurones et les grands modèles de langage. Comprenez les concepts, voyez des exemples concrets et expérimentez avec des démonstrations interactives.
12 questions
Fondamentaux de l’IA5 min de lecture
What Is a Neural Network?
What a neuron computes, why a hidden layer needs a non-linearity, and a worked example you can check on paper.
Apprentissage automatique4 min de lecture
How Does Backpropagation Work?
The chain rule as a credit-assignment algorithm, with a one-weight example you can check by hand and the role of the learning rate.
Apprentissage automatique5 min de lecture
What Is an Embedding in AI?
How meaning becomes geometry, what cosine similarity measures, and why embeddings are the retrieval layer behind modern AI products.
Apprentissage profond4 min de lecture
What Is Self-Attention in Transformers?
How tokens decide what to read, the scaled dot-product formula, causal masking and why long context costs quadratic compute.
Fondamentaux de l’IA4 min de lecture
What Is the Difference Between Training and Inference?
What changes in each phase, why inference is cheaper per request, and why chatting with a model does not retrain it.
Apprentissage automatique4 min de lecture
What Is a Loss Function in Machine Learning?
What a loss rewards, how MSE and cross-entropy differ, and why a low training loss is not the same as a good model.
Fondamentaux de l’IA4 min de lecture
What Are Parameters in an AI Model?
What counts as a parameter, a layer-by-layer count you can verify, and what the number does — and does not — tell you.
Grands modèles de langage4 min de lecture
Why Do AI Models Hallucinate?
Why plausible text is not verified text, how grounding and abstention help, and why hallucination cannot be eliminated entirely.
Grands modèles de langage4 min de lecture
What Does Temperature Do in an LLM?
The softmax formula behind the dial, what low and high values actually do, and why temperature cannot add knowledge.
Grands modèles de langage4 min de lecture
What Is Top-p Sampling?
How the nucleus is chosen, a worked probability example, and how top-p interacts with temperature and top-k.
Grands modèles de langage4 min de lecture
Why Does ChatGPT Give Different Answers to the Same Prompt?
Sampling as the main cause, the other four sources of variation, and the settings that make outputs reproducible enough to test.
Fondamentaux de l’IA4 min de lecture
What Is the Difference Between AI, Machine Learning and Deep Learning?
The nested relationship between the three terms, a concrete example at each level, and why the distinction changes your engineering choices.