Open course
EN · AR · no accountFNX 101AI Studio — Intro to AI
Ten days from your first dataset to your own AI Studio. Read each day's briefing deck, then run the lab notebook right here — cells stream their real results, no setup required.
A hands-on introduction to AI told as a story: you join the Lab as an AI explorer, and every day you master one pillar of the field — data, supervised and unsupervised learning, neural networks, vision, language, and reinforcement learning — unlocking one module of a web app you assemble on Demo Day.
- Level
- L1· Beginner
- Code
- FNX 101
- Days
- 10
- Labs
- 11
- Studio modules
- 7
- Slides
- 124
- Languages
- English · العربية
- Cost
- $0 · no account
Syllabus
FNX 101 · 01–10Week 1
Foundations — data to neural nets- 01Not started
Welcome to the Lab
Become a data detective: clean a real penguin dataset with pandas, then tour the AI models you'll build all course.
data literacypandascleaningscatter plotsEngine day13 slides2 labsEN · AR - 02Not started
Teaching Machines with Examples
Supervised learning from scratch: k-Nearest Neighbors, decision trees, and the sacred train/test split.
supervised learningk-NNdecision treestrain/test splitUnlocks · Prediction Machine12 slides1 labEN · AR - 03Not started
Finding Hidden Patterns
Unsupervised learning: discover clusters with k-means and compare them with the real species, then map high-dimensional data with PCA, t-SNE, and UMAP.
unsupervised learningk-meansPCAt-SNEUMAPUnlocks · Pattern Finder12 slides1 labEN · AR - 04Not started
Inside the Brain
Build a neural network from scratch in pure NumPy — neurons, layers, gradient descent — and meet the matrix multiplication hiding underneath.
neural networksNumPygradient descentmatrix multiplicationEngine day13 slides1 labEN · AR - 05Not started
Superpowers: PyTorch + GPU
Trade your NumPy net for PyTorch and a GPU: autograd, MNIST, and a digit reader that deciphers real handwriting.
PyTorchautogradMNISTGPU trainingUnlocks · Digit Reader12 slides1 labEN · AR
Week 2
Frontiers — vision, language, action- 06Not started
Machines That See
Convolutions turn pixels into perception: train a CNN photo detective on CIFAR-10's ten everyday classes.
CNNsconvolutionsCIFAR-10computer visionUnlocks · Photo Detective12 slides1 labEN · AR - 07Not started
Standing on Giants' Shoulders
Borrow a pre-trained network's eyes and teach it rock-paper-scissors from just 36 photos — transfer learning in action.
transfer learningMobileNetfeature extractionwebcam inferenceUnlocks · RPS Arena13 slides1 labEN · AR - 08Not started
Machines That Read
Tokenizers, embeddings, and attention: open up GPT-2, watch it predict one token at a time, and build your own language lab.
tokenizersembeddingsattentiontransformersGPT-2Unlocks · Language Lab13 slides1 labEN · AR - 09Not started
Machines That Act
Reinforcement learning: a Q-table agent crosses a frozen lake, then a deep Q-network learns to balance a pole from reward alone.
reinforcement learningQ-learningFrozenLakeDQNCartPoleUnlocks · Game Master12 slides1 labEN · AR - 10Not started
Demo Day
Assemble all seven modules into one running Studio, present it with honest model cards, and run the Grand Benchmark that reveals the operation beneath everything.
demomodel cardsbenchmarkingmatmulthe big revealUnlocks · The Full Studio12 slides1 labEN · AR