Abstract
Many deep architectures have been proposed in recent years. To obtain good results, most of the previous deep models need a large number of training data. In this paper, for small and middle scale applications, we propose a novel deep learning framework based on stacked feature learning models. Particularly, we stack marginal Fisher analysis (MFA) layer by layer for the initialization of the deep architecture and call it Marginal Deep Architectures (MDA). In the implementation of MDA, the weight matrices of MFA are first learned layer by layer, and then some deep learning techniques are employed to fine tune the deep architecture. To evaluate the effectiveness of MDA, we have compared it with related feature learning methods and deep learning models on six small and middle scale real-world applications. Extensive experiments demonstrate that MDA performs not only better than shallow feature learning models, but also deep learning models in these applications.
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.
