Demystifying Deep Learning: A Geometric Approach to Iterative Projections
This work addresses training challenges in deep learning for researchers, offering an alternative approach that is incremental in nature.
The paper tackles the difficult training of deep learning models by proposing a semi-parametric framework with geometric regularization, showing it relates to ResNet architectures and can be easily trained to obtain complex structures.
Parametric approaches to Learning, such as deep learning (DL), are highly popular in nonlinear regression, in spite of their extremely difficult training with their increasing complexity (e.g. number of layers in DL). In this paper, we present an alternative semi-parametric framework which foregoes the ordinarily required feedback, by introducing the novel idea of geometric regularization. We show that certain deep learning techniques such as residual network (ResNet) architecture are closely related to our approach. Hence, our technique can be used to analyze these types of deep learning. Moreover, we present preliminary results which confirm that our approach can be easily trained to obtain complex structures.