Probability distribution representation
Kernel Density Matrices
Introduced by González et al. in Kernel Density Matrices for Probabilistic Deep LearningKernel density matrices provide a simpler yet effective mechanism for representing joint probability distributions of both continuous and discrete random variables. This abstraction allows the construction of differentiable models for density estimation, inference, and sampling, and enables their integration into end-to-end deep neural models.
Source: Kernel Density Matrices for Probabilistic Deep LearningPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Generation | 1 | 8.33% |
| Image Manipulation | 1 | 8.33% |
| Optical Flow Estimation | 1 | 8.33% |
| Video Prediction | 1 | 8.33% |
| Blocking | 1 | 8.33% |
| Cover song identification | 1 | 8.33% |
| Disentanglement | 1 | 8.33% |
| Information Retrieval | 1 | 8.33% |
| Music Information Retrieval | 1 | 8.33% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
