Feature Imitating Networks
This approach helps bridge the gap between domain experts and machine learning practitioners by leveraging feature-engineering insights to enhance representation learning.
The paper tackles the challenge of improving neural network performance by introducing Feature-Imitating Networks (FINs), which initialize weights to approximate closed-form statistical features like Shannon's entropy, resulting in best-in-class performance for downstream signal processing and inference tasks with less data and fine-tuning.
In this paper, we introduce a novel approach to neural learning: the Feature-Imitating-Network (FIN). A FIN is a neural network with weights that are initialized to reliably approximate one or more closed-form statistical features, such as Shannon's entropy. In this paper, we demonstrate that FINs (and FIN ensembles) provide best-in-class performance for a variety of downstream signal processing and inference tasks, while using less data and requiring less fine-tuning compared to other networks of similar (or even greater) representational power. We conclude that FINs can help bridge the gap between domain experts and machine learning practitioners by enabling researchers to harness insights from feature-engineering to enhance the performance of contemporary representation learning approaches.