{"content":{"markdown":"How does AI actually work? This learning path answers the question in five levels, from the map of the AI universe to transformers, diffusion models and agents. Instead of repeating textbook claims, the guides show what we measured ourselves, with experiments on a public dataset of handwritten digits that anyone can repeat, and what the history of notable AI models shows, based on Epoch AI's data on more than a thousand models since 1950.","text":"How does AI actually work? This learning path answers the question in five levels, from the map of the AI universe to transformers, diffusion models and agents. Instead of repeating textbook claims, the guides show what we measured ourselves, with experiments on a public dataset of handwritten digits that anyone can repeat, and what the history of notable AI models shows, based on Epoch AI\u0026rsquo;s data on more than a thousand models since 1950.\n","words":74},"date":"2026-10-18","description":"Learn how AI works in five levels: machine learning, neural networks, deep learning, generative AI and agents, explained with our own experiments and data on AI models.","json":"https://abxk.ai/en/ai-development/fundamentals/index.json","kind":"section","language":"en","learning_path":{"category":"ai-development","levels":5},"modified":"2026-10-18","pages":[{"description":"Regression explained with real data: a line through Epoch AI's records of AI models predicts training compute from model size. What slope, R² and errors mean.","json":"https://abxk.ai/en/ai-development/fundamentals/regression-explained/index.json","kind":"page","title":"Regression: How a Model Predicts a Number","url":"https://abxk.ai/en/ai-development/fundamentals/regression-explained/"},{"description":"AI, machine learning, neural networks, deep learning, generative AI and agents explained as one map, with the milestones from 1950 to today in data.","json":"https://abxk.ai/en/ai-development/fundamentals/ai-universe-explained/index.json","kind":"page","title":"The AI Universe: How AI, Machine Learning, Deep Learning and Generative AI Fit Together","url":"https://abxk.ai/en/ai-development/fundamentals/ai-universe-explained/"},{"description":"How to judge a classifier, shown with our digit recognizer: what accuracy hides, what a confusion matrix reveals and how a threshold trades precision for recall.","json":"https://abxk.ai/en/ai-development/fundamentals/classification-metrics/index.json","kind":"page","title":"Classification: Accuracy, Precision and Recall Explained","url":"https://abxk.ai/en/ai-development/fundamentals/classification-metrics/"},{"description":"Supervised, unsupervised and reinforcement learning, shown with our own repeatable experiment: how many examples a model needs and what it learns without any labels.","json":"https://abxk.ai/en/ai-development/fundamentals/how-machines-learn-experiment/index.json","kind":"page","title":"How Machines Learn: An Experiment with Handwritten Digits","url":"https://abxk.ai/en/ai-development/fundamentals/how-machines-learn-experiment/"},{"description":"How a decision tree decides, why a deeper tree scores 100% on its training data and still fails on new data, and how a random forest fixes it, shown with our data.","json":"https://abxk.ai/en/ai-development/fundamentals/decision-trees-overfitting/index.json","kind":"page","title":"Decision Trees and Overfitting: When a Model Learns by Heart","url":"https://abxk.ai/en/ai-development/fundamentals/decision-trees-overfitting/"},{"description":"Training vs inference explained: what happens when an AI model learns and when it answers, what each phase costs and how big frontier training runs are.","json":"https://abxk.ai/en/ai-development/fundamentals/training-and-inference/index.json","kind":"page","title":"Training and Inference: When AI Learns and When It Answers","url":"https://abxk.ai/en/ai-development/fundamentals/training-and-inference/"},{"description":"What parameters, training data and compute mean, how fast each has grown since 2010 according to Epoch AI's data and why more of all three made AI models better.","json":"https://abxk.ai/en/ai-development/fundamentals/parameters-data-compute/index.json","kind":"page","title":"Parameters, Data and Compute: Why AI Models Grew So Fast","url":"https://abxk.ai/en/ai-development/fundamentals/parameters-data-compute/"},{"description":"Six classic methods on the same data, from logistic regression to a neural network, compared fairly with cross-validation, plus what each one costs to run.","json":"https://abxk.ai/en/ai-development/fundamentals/comparing-ml-methods/index.json","kind":"page","title":"Which Algorithm Wins? Six Classic Methods Compared","url":"https://abxk.ai/en/ai-development/fundamentals/comparing-ml-methods/"},{"description":"How k-means finds groups in data nobody labeled, why choosing the number of groups is hard, and how PCA shrinks 64 pixels to a few numbers, tested on real data.","json":"https://abxk.ai/en/ai-development/fundamentals/clustering-and-pca/index.json","kind":"page","title":"Clustering and PCA: Finding Structure Without Labels","url":"https://abxk.ai/en/ai-development/fundamentals/clustering-and-pca/"},{"description":"What a neural network is, shown with a network we trained ourselves: what a neuron computes, what layers and weights do and how size changes accuracy.","json":"https://abxk.ai/en/ai-development/fundamentals/neural-networks-in-plain-words/index.json","kind":"page","title":"Neural Networks in Plain Words: Neurons, Layers and Weights","url":"https://abxk.ai/en/ai-development/fundamentals/neural-networks-in-plain-words/"}],"section":"ai-development","seo_title":"AI Fundamentals: Machine Learning to Generative AI","title":"AI Fundamentals: How AI Works","translations":[{"json":"https://abxk.ai/de/ai-development/fundamentals/index.json","language":"de","url":"https://abxk.ai/de/ai-development/fundamentals/"}],"url":"https://abxk.ai/en/ai-development/fundamentals/"}