Gast ::
| Hauptseite > Publikationsdatenbank > Decomposing neural networks as mappings of correlation functions |
| Hauptseite > Publikationsdatenbank > Decomposing neural networks as mappings of correlation functions |
| Preprint | FZJ-2022-05378 |
; ; ; ; ;
2022
arXiv
This record in other databases:
Please use a persistent id in citations: http://hdl.handle.net/2128/32943 doi:10.48550/ARXIV.2202.04925 doi:10.48550/arXiv.2202.04925
Abstract: Understanding the functional principles of information processing in deep neural networks continues to be a challenge, in particular for networks with trained and thus non-random weights. To address this issue, we study the mapping between probability distributions implemented by a deep feed-forward network. We characterize this mapping as an iterated transformation of distributions, where the non-linearity in each layer transfers information between different orders of correlation functions. This allows us to identify essential statistics in the data, as well as different information representations that can be used by neural networks. Applied to an XOR task and to MNIST, we show that correlations up to second order predominantly capture the information processing in the internal layers, while the input layer also extracts higher-order correlations from the data. This analysis provides a quantitative and explainable perspective on classification.
Keyword(s): Disordered Systems and Neural Networks (cond-mat.dis-nn) ; Machine Learning (stat.ML) ; FOS: Physical sciences ; FOS: Computer and information sciences
|
The record appears in these collections: |
PDF
Volltext