Glossary entry
लर्निङ रेट / सिकाइ दर
Definition (English)
A setting that controls how big each step is when a model updates its parameters.
अर्थ (नेपालीमा)
मोडेलले प्यारामिटर अद्यावधिक गर्दा प्रत्येक पाइला कति ठूलो हुने नियन्त्रण गर्ने सेटिङ।
Related terms
Adam Optimizer
एडम अप्टिमाइजर
A widely used optimizer that adapts the learning rate for each parameter.
Hyperparameter
हाइपरप्यारामिटर
A configuration value set before training that controls how a model learns, like learning rate.
Gradient Descent
ग्र्याडियन्ट डिसेन्ट
An optimization method that gradually reduces error by adjusting parameters step by step.
Greedy Algorithm
लोभी एल्गोरिदम
An approach that makes the best immediate choice at each step, hoping for a good overall result.
Momentum
मोमेन्टम
An optimization trick that uses past updates to speed up and smooth learning.
Q-Learning
क्यू-लर्निङ
A reinforcement learning algorithm that learns the value of actions in each state.
Stride
स्ट्राइड
How many pixels a convolution filter moves at each step across an image.
Temperature
टेम्परेचर
A setting that controls the randomness of a model's output; higher means more varied.