Read the notes, then try the practice. It adapts as you go.When you're ready.
Session Length
~17 min
Adaptive Checks
15 questions
Transfer Probes
8
Machine learning is a branch of artificial intelligence that enables computer systems to learn from data and improve their performance on tasks without being explicitly programmed for every scenario. At its core, machine learning algorithms identify patterns in data and use those patterns to make predictions or decisions. The field is broadly divided into three paradigms: supervised learning, where models are trained on labeled input-output pairs to predict outcomes for new inputs; unsupervised learning, where algorithms discover hidden structure in unlabeled data through clustering or dimensionality reduction; and reinforcement learning, where agents learn optimal behaviors through trial-and-error interaction with an environment, receiving rewards or penalties for their actions.
Deep learning, a powerful subset of machine learning, uses artificial neural networks with many layers to learn hierarchical representations of data. Inspired by the structure of the human brain, deep neural networks have achieved breakthrough results in computer vision, natural language processing, speech recognition, and generative modeling. Architectures such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers have enabled capabilities that were previously considered out of reach, from real-time image classification to human-level language understanding. The success of deep learning has been fueled by the availability of massive datasets, advances in GPU computing, and innovations in optimization algorithms like stochastic gradient descent and the Adam optimizer.
Today, machine learning powers a vast range of real-world applications across virtually every industry. In healthcare, ML models assist in diagnosing diseases from medical images and predicting patient outcomes. In finance, algorithms detect fraudulent transactions and optimize trading strategies. Recommendation systems on platforms like Netflix and Spotify use collaborative filtering and content-based approaches to personalize user experiences. Autonomous vehicles rely on machine learning for perception, planning, and decision-making. As the field continues to evolve, critical topics such as model interpretability, fairness, data privacy, and the responsible deployment of AI systems have become central concerns for researchers and practitioners alike.
One step at a time.
A machine learning paradigm in which models are trained on labeled datasets containing input-output pairs. The algorithm learns a mapping function from inputs to outputs, enabling it to predict correct labels for previously unseen data. Common tasks include classification and regression.
Example: Training a spam filter on thousands of emails labeled as 'spam' or 'not spam,' so it can automatically classify new incoming emails.
A machine learning approach where algorithms learn patterns from unlabeled data without predefined output categories. The system discovers inherent structure, groupings, or relationships within the data on its own. Key techniques include clustering, dimensionality reduction, and anomaly detection.
Example: Using $k$-means clustering on customer purchase data to automatically segment customers into distinct groups for targeted marketing campaigns.
Computational models inspired by the biological neural networks of the human brain, consisting of interconnected layers of artificial neurons (nodes). Each connection has a weight that is adjusted during training, and neurons apply activation functions to produce outputs. Deep neural networks with many hidden layers can learn complex, hierarchical representations of data.
Example: A convolutional neural network (CNN) that processes an image through successive layers, first detecting edges, then shapes, then object parts, and finally recognizing the complete object as a cat or dog.
An iterative optimization algorithm used to minimize a model's loss function by updating parameters in the direction of the steepest decrease of the loss. The learning rate controls the step size, and variants like stochastic gradient descent (SGD) and Adam improve efficiency by using subsets of data or adaptive learning rates.
Example: During training, a neural network uses gradient descent to incrementally adjust its millions of weights so that its predictions on training images get progressively closer to the correct labels.
A modeling error that occurs when a machine learning model learns the training data too well, capturing noise and random fluctuations rather than the underlying pattern. An overfit model performs excellently on training data but poorly on unseen test data. Techniques like regularization, dropout, cross-validation, and early stopping help prevent overfitting.
Example: A decision tree with no depth limit memorizes every training example perfectly, achieving 100% training accuracy, but misclassifies many new test samples because it learned noise rather than generalizable patterns.
A fundamental concept describing the tension between two sources of error in machine learning models. Bias is error from overly simplistic assumptions causing the model to miss relevant patterns (underfitting), while variance is error from excessive sensitivity to training data fluctuations (overfitting). The optimal model balances both to minimize total error.
Example: A linear regression model for housing prices has high bias because it cannot capture nonlinear relationships, while a high-degree polynomial model has high variance because it fits training noise. A moderate-complexity model strikes the best balance.
The process of using domain knowledge to create, transform, or select input variables (features) that improve a machine learning model's predictive performance. Good feature engineering can dramatically boost model accuracy and is often more impactful than choosing a more complex algorithm. It includes tasks like normalization, encoding categorical variables, and creating interaction terms.
Example: For a house price prediction model, engineering features such as 'price per square foot,' 'age of the house,' and 'distance to nearest school' from raw data fields like sale price, area, construction year, and GPS coordinates.
A supervised learning algorithm that makes predictions by recursively splitting data based on feature values, forming a tree-like structure of decisions. Each internal node represents a test on a feature, each branch represents an outcome of that test, and each leaf node holds a prediction. They are intuitive and interpretable but prone to overfitting without pruning or ensemble methods.
Example: A medical diagnosis tree that first checks if a patient's temperature exceeds 38 degrees Celsius, then checks white blood cell count, then checks symptom duration, ultimately classifying the condition as bacterial infection, viral infection, or other.
More terms are available in the glossary.
Choose a different way to engage with this topic — no grading, just richer thinking.
Explore your way — choose one:
See how the key ideas connect. Nodes color in as you practice.
Walk through a solved problem step-by-step. Try predicting each step before revealing it.
This is guided practice, not just a quiz. Hints and pacing adjust in real time.
Small steps add up.
What you get while practicing:
The best way to know if you understand something: explain it in your own words.
More ways to strengthen what you just learned.