A. A model that can process and integrate multiple types of data—such as text, images, and audio—within a unified architecture.

E. A technology that performs AI computation locally on devices rather than relying on cloud servers, reducing latency and bandwidth usage.

H. A training approach enabling a model to learn from only a very small number of labeled examples.

B. A method in which a model learns by generating its own labels from raw data, reducing the need for annotated datasets.

D. A process in which an algorithm automatically designs optimal neural network architectures, often using evolutionary or reinforcement strategies.

I. A system comprising two neural networks—a generator and a discriminator—that compete to produce realistic synthetic data.

J. AI approaches are designed to make model decisions transparent, interpretable, and understandable to humans.

C. A scenario where a neural network loses previously learned information when trained on new data.

F. A paradigm in which an AI agent learns by interacting with its environment, receiving rewards or penalties to optimize behavior.

G. A technique that uses knowledge gained from one task to improve performance on a related but different task.