Generative Models
Sparse Autoencoder
A Sparse Autoencoder is a type of autoencoder that employs sparsity to achieve an information bottleneck. Specifically the loss function is constructed so that activations are penalized within a layer. The sparsity constraint can be imposed with L1 regularization or a KL divergence between expected average neuron activation to an ideal distribution $p$.
Image: Jeff Jordan. Read his blog post (click) for a detailed summary of autoencoders.
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| General Classification | 4 | 7.84% |
| Classification | 3 | 5.88% |
| Denoising | 3 | 5.88% |
| EEG | 2 | 3.92% |
| Electroencephalogram (EEG) | 2 | 3.92% |
| Dimensionality Reduction | 2 | 3.92% |
| Clustering | 2 | 3.92% |
| Small Data Image Classification | 2 | 3.92% |
| Data Compression | 1 | 1.96% |
L1 Regularization
