Restricted Boltzmann Machine
contrastive divergence for training an RBM is presented in details.
現在この提出コンテンツをフォロー中です。
- フォローしているコンテンツ フィードに更新が表示されます。
- コミュニケーション基本設定に応じて電子メールを受け取ることができます
Restricted Boltzmann machines (RBMs) are the first neural networks used for unsupervised learning, created by Geoff Hinton (university of Toronto).
The aim of RBMs is to find patterns in data by reconstructing the inputs using only two layers (the visible layer and the hidden layer). By moving forward an RBM translates the visible layer into a set of numbers that encodes the inputs, in backward pass it takes those set of numbers and translates them to the visible layer to regenerate the inputs.
In this code we introduce to you very simple algorithms that depend on contrastive divergence training. The details of this method are explained step by step in the comments inside the code.
To learn about RBM you can start from these referances:
[1] G. Hinton and G. Hinton, “A Practical Guide to Training Restricted Boltzmann Machines A Practical Guide to Training Restricted Boltzmann Machines,” 2010.
how To use the codes:
https://www.youtube.com/watch?v=uaVfyeE3Jwk&feature=youtu.be
引用
BERGHOUT Tarek (2026). Restricted Boltzmann Machine (https://jp.mathworks.com/matlabcentral/fileexchange/71212-restricted-boltzmann-machine), MATLAB Central File Exchange. に取得済み.
| バージョン | 公開済み | リリース ノート | Action |
|---|---|---|---|
| 3.1.0 | discription |
||
| 3.0.0 | description |
||
| 2.0.0 | new version |
||
| 1.5.0 | referances |
|
|
| 1.4.0 | In the last version we made a mistake: instead of giving all the samples of the image to visible neurons we used only one sample in each Gibbs sampling; now it is corrected. |
|
|
| 1.3.0 | new descriptif image |
|
|
| 1.2.0 | in the last code we trained by mistake the RBM with scalar units in visible and hidden layers, as we change the representation of these units into binary units during training and we'v got a much more improvements in accurcy |
||
| 1.0.0 |
|
