Abstract
AbstractThis paper proposes a new deep learning paradigm in an attempt to provide a new way to break the limitations of existing deep learning. This paper re-examines the rationality of the existing deep learning paradigm, takes supervised learning as the research object, with focusing on the universality and interpretability of the model. Starting from the basic framework, a configurable supervised learning framework is explorably proposed. The complete design process under the proposed framework is demonstrated through a simple regression case, which verifies the feasibility and effectiveness of the framework. In addition, the inspiration of the deep learning paradigm proposed in this paper should be more worthy of attention and consideration.KeywordsDeep learningConfigurable modelReusability model
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.
