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
Artificial Intelligence (AI) is the branch of computer science dedicated to creating systems capable of performing tasks that typically require human intelligence, such as reasoning, learning, perception, and language understanding. The field was formally founded in 1956 at the Dartmouth Conference, where pioneers like John McCarthy, Marvin Minsky, Allen Newell, and Herbert Simon envisioned machines that could simulate every aspect of human cognition. Early AI research focused on symbolic approaches and rule-based expert systems, which achieved impressive results in narrow domains but struggled with the complexity and ambiguity of the real world.
Modern AI is dominated by machine learning and deep learning approaches, where systems learn patterns from vast amounts of data rather than following explicitly programmed rules. Neural networks, inspired loosely by biological neurons, form the backbone of breakthroughs in image recognition, natural language processing, speech synthesis, and game playing. Techniques such as supervised learning, unsupervised learning, and reinforcement learning enable AI systems to classify data, discover hidden structures, and optimize decision-making through trial and error. The transformer architecture, introduced in 2017, revolutionized natural language processing and gave rise to large language models capable of generating human-quality text, code, and creative content.
AI applications now span virtually every industry, from healthcare diagnostics and autonomous vehicles to financial trading and scientific discovery. However, the rapid advancement of AI raises profound ethical questions about bias in algorithms, job displacement, privacy, accountability, and the long-term risks of increasingly autonomous systems. Responsible AI development requires interdisciplinary collaboration among computer scientists, ethicists, policymakers, and the public to ensure that these powerful technologies benefit humanity while minimizing harm.
One step at a time.
A subset of AI in which algorithms improve their performance on a task through experience, without being explicitly programmed for every scenario. Machine learning systems identify patterns in data and use statistical models to make predictions or decisions.
Example: A spam filter that learns to classify emails as spam or not spam by training on thousands of labeled examples, improving its accuracy over time.
Computing systems loosely inspired by the structure of biological neural networks, consisting of layers of interconnected nodes (neurons) that process information. Each connection has a weight that is adjusted during training to minimize prediction errors.
Example: A neural network trained on handwritten digit images (like the MNIST dataset) learns to recognize digits 0-9 by adjusting weights across multiple layers of neurons.
A subfield of machine learning that uses neural networks with many layers (deep architectures) to learn hierarchical representations of data. Deep learning excels at automatically extracting features from raw data without manual feature engineering.
Example: A convolutional neural network with dozens of layers can learn to detect edges, then shapes, then objects in images, enabling accurate photo classification in systems like Google Photos.
The branch of AI concerned with enabling computers to understand, interpret, and generate human language. NLP combines computational linguistics with machine learning to process text and speech data at scale.
Example: Virtual assistants like Siri and Alexa use NLP to parse spoken questions, understand intent, and generate relevant spoken responses.
The field of AI that trains computers to interpret and understand visual information from the world, including images and video. Computer vision systems can detect objects, recognize faces, read text, and analyze scenes.
Example: Self-driving cars use computer vision to identify pedestrians, traffic signs, lane markings, and other vehicles in real time from camera feeds.
A type of machine learning where an agent learns to make decisions by performing actions in an environment and receiving rewards or penalties. The agent aims to maximize cumulative reward over time through exploration and exploitation.
Example: DeepMind's AlphaGo used reinforcement learning to master the game of Go, training by playing millions of games against itself and learning which strategies lead to wins.
A machine learning approach where the model is trained on labeled data, meaning each training example includes both the input and the correct output. The model learns to map inputs to outputs and generalize to unseen data.
Example: Training a model on thousands of chest X-rays labeled as 'pneumonia' or 'healthy' so it can diagnose new patients' X-rays automatically.
A machine learning approach where the model is trained on data without labeled outputs, and must discover hidden patterns, groupings, or structures on its own. Common techniques include clustering and dimensionality reduction.
Example: A retailer uses unsupervised clustering on customer purchase data to discover distinct customer segments for targeted marketing campaigns.
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.