MemorySamplingStrategy
Enums · AiDotNet.ContinualLearning.Interfaces
Memory sampling strategies for experience replay.
For Beginners
When storing examples from previous tasks, the sampling strategy determines how examples are selected and maintained in memory.
Fields
| Field | Summary |
|---|---|
MemorySamplingStrategy Boundary |
Boundary-focused sampling selects examples near decision boundaries. |
MemorySamplingStrategy ClassBalanced |
Class-balanced sampling ensures equal representation of each class. |
MemorySamplingStrategy GradientBased |
Gradient-based sample selection. |
MemorySamplingStrategy Herding |
Herding-based selection picks examples closest to class means. |
MemorySamplingStrategy KCenter |
K-Center coreset selection maximizes coverage of the feature space. |
MemorySamplingStrategy Random |
Random uniform sampling from the dataset. |
MemorySamplingStrategy Reservoir |
Reservoir sampling - uniform random selection. |
MemorySamplingStrategy RingBuffer |
Ring buffer - FIFO replacement. |
int value__ |