Zero-Shot Learning
Quick Definition
Performing tasks on unseen classes without training examples
Full Definition
A ML paradigm where a model performs tasks on unseen classes without any training examples for those classes.
Examples
image classification of new categories, cross-domain transfer
Related Terms
few-shot-learning
transfer-learning
meta-learning
More Artificial Intelligence Terms
AI Benchmark
Standardized tests measuring AI model performance
Synthetic Data
Artificially generated data mimicking real-world distributions
Sentiment Analysis
NLP technique determining emotional tone in text
Federated Learning
Distributed ML training without sharing raw data
Adversarial Robustness
AI model ability to resist adversarial perturbations
Pruning
Removing redundant neural network connections to reduce size