Exponential Decay is a learning rate schedule where we decay the learning rate with more iterations using an exponential function:
$$ \text{lr} = \text{lr}_{0}\exp\left(-kt\right) $$
Image Credit: Suki Lau
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 13 | 14.94% |
Computational Efficiency | 5 | 5.75% |
Classification | 5 | 5.75% |
Time Series Analysis | 4 | 4.60% |
Reinforcement Learning (RL) | 3 | 3.45% |
General Classification | 3 | 3.45% |
Language Modelling | 2 | 2.30% |
Knowledge Tracing | 2 | 2.30% |
Multi-agent Reinforcement Learning | 2 | 2.30% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |