DBN is a probability generation model. Compared with the neural network of the traditional discrimination model, the DBN is to establish a joint distribution between observation data and labels. By training the weights among its neurons, the whole neural network can generate training data according to the maximum probability.
Input variable: image
Output variable: Recognized image
Contact SupportNorthwest Institute of Eco-Environment and Resources, CAS 0931-4967287 email@example.com
LinksNational Tibetan Plateau Data Center