10 terms
Showing all terms starting with E
Numerical vector representations of text, images, or other data that capture semantic meaning, enabling similarity search and retrieval.
Unexpected capabilities that arise in large AI models at scale, not explicitly programmed or present in smaller versions.
A neural network architecture where an encoder compresses input into a latent representation and a decoder generates the output from it.
One complete pass through the entire training dataset during model training. Multiple epochs are typically needed for convergence.
Running AI inference on local devices (phones, IoT sensors, edge servers) rather than in the cloud, reducing latency and improving privacy.
A technique that combines predictions from multiple models to produce a more accurate and robust result than any single model alone.
An NLP task that identifies and classifies named entities such as people, organisations, locations, and dates in unstructured text.
Quantitative measures used to assess model performance, such as accuracy, F1 score, BLEU, ROUGE, perplexity, or AUC-ROC.
An early form of AI that encodes human domain knowledge as rules to solve specific problems, predating modern machine learning approaches.
The degree to which an AI model's predictions or decisions can be understood and interpreted by humans, critical for trust and compliance.
