Incorporating Prior Knowledge into Neural Networks through an Implicit Composite Kernel. (arXiv:2205.07384v2 [cs.LG] UPDATED)

It is challenging to guide neural network (NN) learning with prior knowledge.
In contrast, many known properties, such as spatial smoothness or seasonality,
are straightforward to model by choosing an appropriate kernel in a Gaussian
process (GP). Many deep learning applications could be enhanced by modeling
such known properties. For example, convolutional neural networks (CNNs) are
frequently used in remote sensing, which is subject to strong seasonal effects.
We propose to blend the strengths of deep learning and the clear …

arxiv kernel knowledge networks neural networks prior