Generative Models
Deep Boltzmann Machine
A Deep Boltzmann Machine (DBM) is a three-layer generative model. It is similar to a Deep Belief Network, but instead allows bidirectional connections in the bottom layers. Its energy function is as an extension of the energy function of the RBM:
$$ E\left(v, h\right) = -\sum^{i}_{i}v_{i}b_{i} - \sum^{N}_{n=1}\sum_{k}h_{n,k}b_{n,k}-\sum_{i, k}v_{i}w_{ik}h_{k} - \sum^{N-1}_{n=1}\sum_{k,l}h_{n,k}w_{n, k, l}h_{n+1, l}$$
for a DBM with $N$ hidden layers.
Source: On the Origin of Deep Learning
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Retrieval | 3 | 16.67% |
| Information Retrieval | 2 | 11.11% |
| General Classification | 2 | 11.11% |
| Benchmarking | 1 | 5.56% |
| Reinforcement Learning (RL) | 1 | 5.56% |
| Denoising | 1 | 5.56% |
| Image Classification | 1 | 5.56% |
| Topic Models | 1 | 5.56% |
| Classification | 1 | 5.56% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
