IB Digital Society - Artificial Intelligence

Artificial Intelligence

The simulation of human intelligence processes by machines, especially computer systems.

Narrow AI

AI systems designed to perform a specific task or a narrow range of tasks.

General AI

Hypothetical AI systems with generalized cognitive abilities that can understand, learn, and apply knowledge across a wide range of tasks.

AI agent

The learner or decision-maker in a reinforcement learning system.

Reinforcement Learning

A type of machine learning where an agent learns to make decisions by performing actions in an environment to achieve maximum cumulative reward.

Neural Network

A computational model inspired by the human brain, consisting of layers of interconnected nodes or neurons.

Deep Learning

A subset of machine learning involving neural networks with many layers that can model high-level abstractions in data.

Supervised Learning

A type of machine learning where the model is trained on labeled data.

Unsupervised Learning

A type of machine learning where the model learns from data without labeled responses, identifying patterns and structures.

Convolutional Neural Network

A type of deep learning model specialized for processing grid-like data, such as images.

Activation Function in a Neural Network

A function that introduces non-linearity into the network, allowing it to learn more complex patterns.

Turing Test

A measure of a machine's ability to exhibit intelligent behavior indistinguishable from that of a human.

Reinforcement Learning Policy

A strategy used by the agent to decide which actions to take, given the current state.

Bias in AI

Systematic and unfair discrimination against certain groups within AI algorithms, often due to biased training data.

Explainable AI

AI systems designed to be transparent and understandable, allowing users to comprehend how decisions are made.

Alignment problem in AI

Ensuring that advanced AI systems’ goals and actions are aligned with human values and interests.

Autoencoder

A type of neural network used for unsupervised learning tasks such as dimensionality reduction or denoising.

Generative Adversarial Network

A type of neural network consisting of two networks, a generator and a discriminator, that compete with each other to create realistic data.

Overfitting

When a model learns the training data too well, including noise and details, resulting in poor generalization to new data.

Loss Function

A function that measures the difference between the predicted output and the actual output, guiding the training process.