Results for "updates"
Online Learning
Intermediate
Learning where data arrives sequentially and the model updates continuously, often under changing distributions.
Concept Drift
Intermediate
The relationship between inputs and outputs changes over time, requiring monitoring and model updates.
Gradient Descent
Intermediate
Iterative method that updates parameters in the direction of negative gradient to minimize loss.
Learning Rate
Intermediate
Controls the size of parameter updates; too high diverges, too low trains slowly or gets stuck.
Few-Shot Learning
Intermediate
Achieving task performance by providing a small number of examples inside the prompt without weight updates.
Federated Learning
Intermediate
Training across many devices/silos without centralizing raw data; aggregates updates, not data.
Trust Region
Intermediate
Restricting updates to safe regions.