High-Order Tensor Regression in Sparse Convolutional Neural Networks
This work addresses convolution methods for sparse convolutional neural networks, presenting a novel paradigm.
The paper tackles the problem of convolution in neural networks by introducing a high-order tensor regression approach, redefining the Backpropagation Algorithm into a simpler, generic form as a result.
This article presents a generic approach to convolution that significantly differs from conventional methodologies in the current Machine Learning literature. The approach, in its mathematical aspects, proved to be clear and concise, particularly when high-order tensors are involved. In this context, a rational theory of regression in neural networks is developed, as a framework for a generic view of sparse convolutional neural networks, the primary focus of this study. As a direct outcome, the classic Backpropagation Algorithm is redefined to align with this rational tensor-based approach and presented in its simplest, most generic form.