International Machine Learning Competition (IMLC)

Ressources et liens

Cette page propose plusieurs liens vers des supports, des applications web, des organisations et plus encore. Tous peuvent être utilisés par les ambassadors, les enseignants et les participants pour entrer en contact avec machine learning et pour perfectionner leurs compétences en machine learning.

Autres collections de ressources : Présentations ↗ Notes de cours ↗

🔗 Elements of AI

↗https://www.elementsofai.com/
"A free introductory course that explains what artificial intelligence and machine learning are in plain language. It uses simple examples and exercises and assumes no programming or math background."

🔗 Google Introduction to Machine Learning

↗https://developers.google.com/machine-learning/intro-to-ml
"A short reading course that defines machine learning and describes the main types such as supervised and unsupervised learning. It is written for beginners and sets up the longer Google crash course."

🔗 Machine Learning for Everyone

↗https://vas3k.com/blog/machine_learning/
"An illustrated long read that walks through the main branches of machine learning with cartoons and everyday analogies. It covers classification, clustering, neural networks, and more without heavy math."

🔗 Google Machine Learning Crash Course

↗https://developers.google.com/machine-learning/crash-course
"A structured course with video lessons, readings, and interactive exercises covering core machine learning concepts. Topics include linear models, neural networks, and how to train and evaluate models."

🔗 Kaggle Learn Intro to Machine Learning

↗https://www.kaggle.com/learn/intro-to-machine-learning
"A hands-on mini course that builds and validates your first models directly in the browser. It introduces decision trees, random forests, and the idea of overfitting through short coding notebooks."

🔗 Explained Visually

↗https://setosa.io/ev/
"A collection of interactive visual explanations of foundational concepts like principal component analysis and conditional probability. Sliders and animations let you build intuition before seeing any formulas."

🔗 Seeing Theory

↗https://seeing-theory.brown.edu/
"A visual introduction to probability and statistics built around interactive animations. It covers distributions, Bayesian inference, and regression, which are the statistical foundations behind machine learning."

🔗 Khan Academy Linear Algebra

↗https://www.khanacademy.org/math/linear-algebra
"A free course covering vectors, matrices, and transformations with videos and practice problems. These topics are the mathematical foundation for representing data and computations in machine learning."

🔗 MLU-Explain Linear Regression

↗https://mlu-explain.github.io/linear-regression/
"An interactive article that explains how linear regression fits a line to data to make predictions. You can drag points and see how the model and its error change in real time."

🔗 MLU-Explain Decision Trees

↗https://mlu-explain.github.io/decision-tree/
"A visual walkthrough of how decision trees split data into branches to classify or predict. Interactive diagrams show how the tree grows and how depth affects its decisions."

🔗 Stanford CS229 Supervised Learning Cheatsheet

↗https://stanford.edu/~shervine/teaching/cs-229/cheatsheet-supervised-learning
"A concise reference summarizing classic supervised algorithms including SVMs, k-nearest neighbors, and naive Bayes. It gives the key formulas and intuition for each method on a single page."

🔗 Google Clustering Course

↗https://developers.google.com/machine-learning/clustering
"A focused course on unsupervised clustering, centered on the k-means algorithm. It explains how to group unlabeled data by similarity and how to measure cluster quality."

🔗 scikit-learn User Guide

↗https://scikit-learn.org/stable/user_guide.html
"The official documentation for scikit-learn, the most widely used machine learning library in Python. It explains each algorithm with practical code examples for classification, regression, and clustering."

🔗 MLU-Explain Bias and Variance

↗https://mlu-explain.github.io/bias-variance/
"An interactive explainer of the bias-variance tradeoff and why models overfit or underfit. Visual examples show how model complexity affects performance on new data."

🔗 MLU-Explain Train, Test, and Validation

↗https://mlu-explain.github.io/train-test-validation/
"A visual guide to splitting data into training, validation, and test sets. It explains why this separation is needed to measure how well a model generalizes."

🔗 An Overview of Gradient Descent

↗https://ruder.io/optimizing-gradient-descent/
"A clear article explaining gradient descent, the optimization method used to train most machine learning models. It compares common variants such as stochastic gradient descent, momentum, and Adam."

🔗 3Blue1Brown Neural Networks

↗https://www.3blue1brown.com/topics/neural-networks
"A celebrated video series that visually explains how neural networks work, from single neurons to backpropagation. The animations build deep intuition for how a network learns from examples."

🔗 MLU-Explain Neural Networks

↗https://mlu-explain.github.io/neural-networks/
"An interactive article that shows how layers of neurons transform inputs into predictions. You can adjust the network and watch how it learns to separate data."

🔗 TensorFlow Playground

↗https://playground.tensorflow.org/
"A browser tool that lets you build and train a small neural network by clicking. You can change features, layers, and activation functions and instantly see how the network learns to classify points."

🔗 Teachable Machine

↗https://teachablemachine.withgoogle.com/
"A Google tool that lets you train a machine learning model in your browser using your webcam or sound. It shows how image and audio classification work without writing any code."

🔗 fast.ai

↗https://www.fast.ai/
"A free practical deep learning course and blog aimed at learners who want to build working models quickly. It teaches modern techniques with a hands-on, code-first approach."

🔗 Dive into Deep Learning

↗https://d2l.ai/
"An interactive deep learning book that combines runnable code, math, and theory in Jupyter notebooks. It covers modern deep learning from the fundamentals through to advanced architectures."

🔗 CNN Explainer

↗https://poloclub.github.io/cnn-explainer/
"An interactive visualization of how a convolutional neural network processes an image layer by layer. You can hover over each step to see how filters detect edges, textures, and shapes."

🔗 Stanford CS231n

↗https://cs231n.github.io/
"The course notes for Stanford's introduction to convolutional neural networks for visual recognition. They explain the core ideas of computer vision and deep learning with clear examples."

🔗 Hugging Face NLP Course

↗https://huggingface.co/learn/nlp-course/chapter1/1
"A free course on natural language processing using modern transformer models. It teaches how machines process text for tasks like classification, translation, and question answering."

🔗 The Illustrated Word2vec

↗https://jalammar.github.io/illustrated-word2vec/
"A visual explanation of word embeddings, which turn words into numbers that capture meaning. It shows how these vectors let machines measure how similar two words are."

🔗 The Illustrated Transformer

↗https://jalammar.github.io/illustrated-transformer/
"A widely cited visual guide to the transformer, the architecture behind modern language models. It breaks down attention and encoder-decoder structure with clear step-by-step diagrams."

🔗 Transformer Explainer

↗https://poloclub.github.io/transformer-explainer/
"An interactive tool that runs a real GPT model in your browser and visualizes how it predicts the next word. You can type text and watch attention and probabilities update live."

🔗 LLM Visualization

↗https://bbycroft.net/llm
"A 3D interactive walkthrough of how a large language model processes tokens through its layers. It makes the internal steps of models like GPT concrete and explorable."

🔗 Diffusion Explainer

↗https://poloclub.github.io/diffusion-explainer/
"An interactive visualization of how diffusion models generate images from text prompts. It shows the step-by-step denoising process behind modern image generators."

🔗 OpenAI Spinning Up in Deep RL

↗https://spinningup.openai.com/en/latest/
"An educational resource that introduces reinforcement learning, where agents learn by trial and error. It explains the core concepts and algorithms with clear writing and code."

🔗 Distill

↗https://distill.pub/
"A journal of clear, interactive explanations of machine learning research. Its visual articles make advanced topics like attention and feature visualization approachable."

🔗 Hugging Face Papers

↗https://huggingface.co/papers
"A daily feed of trending machine learning papers, each linked to code, models, and demos. It is useful for seeing current work and finding reference implementations."

🔗 Machine Learning Mastery

↗https://machinelearningmastery.com/
"A blog with practical, beginner-friendly tutorials on machine learning algorithms and workflows. Each article focuses on getting a working result with clear code and explanations."

🔗 Google Machine Learning Fairness

↗https://developers.google.com/machine-learning/crash-course/fairness/types-of-bias
"An overview of fairness in machine learning and how models can reflect or amplify bias. It introduces types of bias and practices for building more responsible systems."