Prototype-based Neural Network Layers: Incorporating Vector Quantization
This work addresses the problem of improving neural network robustness and interpretability for machine learning practitioners, but it is incremental as it builds on existing prototype-based methods.
The paper tackles the lack of robustness and interpretability in neural networks by proposing techniques to merge them with prototype-based vector quantization methods, focusing on constructing prototype-based classification layers and convolution operations without presenting numerical results.
Neural networks currently dominate the machine learning community and they do so for good reasons. Their accuracy on complex tasks such as image classification is unrivaled at the moment and with recent improvements they are reasonably easy to train. Nevertheless, neural networks are lacking robustness and interpretability. Prototype-based vector quantization methods on the other hand are known for being robust and interpretable. For this reason, we propose techniques and strategies to merge both approaches. This contribution will particularly highlight the similarities between them and outline how to construct a prototype-based classification layer for multilayer networks. Additionally, we provide an alternative, prototype-based, approach to the classical convolution operation. Numerical results are not part of this report, instead the focus lays on establishing a strong theoretical framework. By publishing our framework and the respective theoretical considerations and justifications before finalizing our numerical experiments we hope to jump-start the incorporation of prototype-based learning in neural networks and vice versa.