Glossary entry
पूर्वाग्रह (एआईमा)
Definition (English)
Systematic unfairness in AI outputs, often reflecting biases present in training data.
अर्थ (नेपालीमा)
एआई नतिजामा देखिने व्यवस्थित अन्याय, जुन प्रायः तालिम डाटाको पूर्वाग्रह झल्काउँछ।
Related terms
Algorithmic Bias
एल्गोरिदमिक पूर्वाग्रह
Unfair outcomes produced by an algorithm, often due to biased data or design.
Inductive Bias
आगमनात्मक पूर्वाग्रह
The set of assumptions a model uses to generalize from training data to new cases.
Supervised Learning
पर्यवेक्षित सिकाइ
Training a model on labeled examples so it learns to map inputs to known outputs.
Automation Bias
स्वचालन पूर्वाग्रह
The tendency of people to over-trust suggestions made by automated systems.
Avatar
अवतार
A digital character or representation of a person, often AI-generated or animated.
Bagging
ब्यागिङ
Training many models on random data subsets and averaging them to reduce variance.
Batch
ब्याच
A small subset of training data processed together in one step of training.
Batch Normalization
ब्याच नर्मलाइजेसन
A technique that stabilizes and speeds up training by normalizing layer inputs.