Fuzzy Restricted Boltzmann Machine for the Enhancement of Deep Learning


Fuzzy Restricted Boltzmann Machine for the Enhancement of Deep Learning


In recent times, deep learning caves out a research wave in machine learning. With outstanding performance, a lot of and additional applications of deep learning in pattern recognition, image recognition, speech recognition, and video processing have been developed. Restricted Boltzmann machine (RBM) plays an vital role in current deep learning techniques, as most of existing deep networks are primarily based on or connected to it. For regular RBM, the relationships between visible units and hidden units are restricted to be constants. This restriction can certainly downgrade the representation capability of the RBM. To avoid this flaw and enhance deep learning capability, the fuzzy restricted Boltzmann machine (FRBM) and its learning algorithm are proposed in this paper, in which the parameters governing the model are replaced by fuzzy numbers. This method, the initial RBM becomes a special case in the FRBM, when there is no fuzziness within the FRBM model. In the process of learning FRBM, the fuzzy free energy perform is defuzzified before the likelihood is outlined. The experimental results based on bar-and-stripe benchmark inpainting and MNIST handwritten digits classification issues show that the illustration capability of FRBM model is significantly higher than the ancient RBM. Additionally, the FRBM additionally reveals higher robustness property compared with RBM when the coaching data are contaminated by noises.

Did you like this research project?

To get this research project Guidelines, Training and Code… Click Here


Leave a Reply

Your email address will not be published. Required fields are marked *

+ forty one = forty two