What is Zero-Shot Learning?

Skill Level:

Zero-Shot Learning is an AI approach that enables models to learn to recognise new classes or concepts without explicit training examples. This is achieved by leveraging existing knowledge and transferring it to unseen classes. Zero-Shot Learning is useful when acquiring labelled data for all possible classes is challenging or unfeasible.

Other Definitions

Edge Computing brings computing resources closer to the source of data generation, reducing latency and improving response times. By processing and analysing data locally…
Adversarial machine learning involves studying and defending AI models against attacks or adversarial examples designed to deceive the system. By understanding vulnerabilities and deploying…
Knowledge Graphs are a structured representation of knowledge that captures relationships between entities. They organise information in a way that allows machines to understand…
Decision networks, also known as Probabilistic Graphical Models, are a type of AI model that represents uncertain knowledge using a graph structure. Decision Networks…