NeuralQuest

Learn how AI really works by building it: label the data and train a classifier, then investigate how a recommender can quietly narrow what you see.

Level 1

Classifier Trainer

Be the teacher: label a handful of examples, watch an AI discover a rule from your labels, then predict what it does on a brand-new example. Find where its training data was unfair and fix it.

Train a classifier →

Recommendation Lab

Predict what a recommender feeds you next, then see how filter bubbles, popularity bias, and feedback loops can quietly shrink your world — and how good recommenders keep discovery open.

Investigate a recommender →

Training Loop

Train a model one round at a time. The training score keeps climbing — but watch the test score on new examples: it peaks, then falls as the model starts to memorize. Learn when to stop before it overfits.

Train & know when to stop →

Does it Generalize?

Several AIs trained up — but the highest training score can be a trap. Predict which model still knows the way on data it has never seen, then reveal the new-data scores and catch the overfit.

Spot the overfit →

Weigh It

A real AI choice has weights on both sides. Read what it helps with and what to watch out for, then pick the decision that weighs both — a balance beam shows if your choice stays level.

Weigh the decision →

Play together

A quick machine-learning face-off for 2–4 players — same device, or an online room by code.

ML Duel (pass-and-play) 2–4 players take turns on one device — same questions, highest first-try score wins. Or open an online room by code.

Concepts — choose a kit

Each kit is a short round of questions with hints when you need them. Your progress stays on this device.

ML Quest — follow the map → A path through all 16 kits, from how machines learn to AI in society. Clear each stop, then move on. Kit 1: how_machines_learn_gr45 How machines learn · grades · 25 questions Kit 2: training_your_first_classifier_gr45 How machines learn · grades · 25 questions Kit 3: neural_networks_and_deep_learning_gr56 Neural networks · grades · 25 questions Kit 4: recommendation_systems_and_personalization_gr56 Recommendation systems · grades · 25 questions Kit 5: bias_fairness_and_data_ethics_gr67 Ethics & bias · grades · 25 questions Kit 6: computer_vision_and_image_ai_gr67 Computer vision · grades · 25 questions Kit 7: natural_language_processing_and_ai_communication_gr78 Language AI · grades · 25 questions Kit 8: master_ai_scientist_responsible_ai_capstone_gr78 Review & synthesis · grades · 25 questions Kit 9: Reinforcement Learning and AI Agents How machines learn · grades 4-5 · 25 questions Kit 10: Generative AI and Creative Machines How machines learn · grades 5-6 · 25 questions Kit 11: AI in Society and Everyday Life Ethics & bias · grades 6-7 · 25 questions Kit 12: Future of AI and Emerging Technologies Future of AI · grades 7-8 · 25 questions Kit 13: Cross-Topic Connections Review & synthesis · grades 5-6 · 25 questions Kit 14: Real-World Applications Review & synthesis · grades 6-7 · 25 questions Kit 15: Misconceptions & Reasoning Review & synthesis · grades 6-7 · 25 questions Kit 16: Advanced Synthesis Review & synthesis · grades 7-8 · 25 questions
NeuralQuest mascot

Meet the cast — the characters who teach this

Each one stands for an idea you’ll practice. Tap a character to read their illustrated story and hear their audio drama.

Explore all the stories →

Kids also liked

PlayAIForgeAppNeuralQuestAppAiForgePlayWonderForgePlayTableForgePlayRoboForge

Privacy & how it works