Glossary entry
Adversarial Attack
प्रतिकूल आक्रमण
Definition (English)
Deliberately crafted inputs designed to fool an AI model into making mistakes.
अर्थ (नेपालीमा)
एआई मोडेललाई गल्ती गर्न छक्याउन जानाजान बनाइएका इनपुट।
Glossary entry
प्रतिकूल आक्रमण
Definition (English)
Deliberately crafted inputs designed to fool an AI model into making mistakes.
अर्थ (नेपालीमा)
एआई मोडेललाई गल्ती गर्न छक्याउन जानाजान बनाइएका इनपुट।
Related terms
Recurrent Neural Network (RNN)
रिकरेन्ट न्युरल नेटवर्क
A network designed for sequences that remembers previous inputs as it processes data.
Artificial Intelligence (AI)
कृत्रिम बुद्धिमत्ता
The field of building machines and software that can perform tasks normally requiring human intelligence, such as reasoning, learning, and decision-making.
Batch Inference
ब्याच इन्फरेन्स
Running predictions on many inputs together rather than one at a time.
Batch Normalization
ब्याच नर्मलाइजेसन
A technique that stabilizes and speeds up training by normalizing layer inputs.
Classification
वर्गीकरण
A task where the model assigns inputs to one of several predefined categories.
Conditioning
कन्डिसनिङ
Guiding a generative model's output using extra inputs like text, images, or labels.
Curse of Dimensionality
आयामको अभिशाप
Problems that arise when data has too many features, making learning harder.
Data-Driven Decision Making
डाटा-आधारित निर्णय
Basing business choices on data and analysis rather than intuition alone.