Glossary entry
Inference Endpoint
इन्फरेन्स एन्डपोइन्ट
Definition (English)
A network address where applications send inputs to get model predictions.
अर्थ (नेपालीमा)
एप्लिकेसनले मोडेल अनुमान पाउन इनपुट पठाउने नेटवर्क ठेगाना।
Related terms
Other terms related to Inference Endpoint.
-
Batch Inference
ब्याच इन्फरेन्स
Running predictions on many inputs together rather than one at a time.
-
Inference
इन्फरेन्स
Running a trained model to generate outputs or predictions on new inputs.
-
Model Serving
मोडेल सर्भिङ
Hosting a trained model so applications can send it requests and get predictions.
-
Neuron (Node)
न्युरन / नोड
A single computing unit in a neural network that combines inputs and produces an output.
-
Recurrent Neural Network (RNN)
रिकरेन्ट न्युरल नेटवर्क
A network designed for sequences that remembers previous inputs as it processes data.
-
Accuracy
शुद्धता
The proportion of predictions a model gets correct out of all predictions.
-
Adversarial Attack
प्रतिकूल आक्रमण
Deliberately crafted inputs designed to fool an AI model into making mistakes.
-
Autoencoder
अटोइन्कोडर
A network that compresses data into a compact code and reconstructs it, useful for learning features.