Abstract
Restricted Boltzmann Machine (RBM) has been widely used technologies in the field of deep learning. The RBM model provides good technical support for implementing various parallelisms. Deep Belief Networks are composed of a set of RBMs, and the performance of the DBN model depends in part on the performance of the RBM model. However, the performance of the RBM model affected by the parameters is its main drawback. How to correctly and effectively fine-tune the parameters of the RBM model has not been completely addressed. In this paper, The Ant Lion Optimization (ALO) Algorithm we mentioned is the latest intelligent optimization algorithm, which has good optimization performance and robustness. So, in order to verify our proposed method. First, ALO algorithm and PSO algorithm are used separately to fine-tune the parameters of RBM model, then DBN model stacked by adjusted RBM models are used for image classification. Experimental verifications are conducted on MNIST dataset. The results show that the ALO algorithm has better results.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
