Neuronal Correlation: a Central Concept in Neural Network
Not on the map. Why?
Abstract (arXiv)
This paper proposes to study neural networks through neuronal correlation, a statistical measure of correlated neuronal activity on the penultimate layer. We show that neuronal correlation can be efficiently estimated via weight matrix, can be effectively enforced through layer structure, and is a strong indicator of generalisation ability of the network. More importantly, we show that neuronal correlation significantly impacts on the accuracy of entropy estimation in high-dimensional hidden spaces. While previous estimation methods may be subject to significant inaccuracy due to implicit assumption on neuronal independence, we present a novel computational method to have an efficient and authentic computation of entropy, by taking into consideration the neuronal correlation. In doing so, we install neuronal correlation as a central concept of neural network.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 10 of its 33 references that are in the map. First posted on arXiv 22 Jan 2022.
Builds on
10 of 33 references.
References · 10
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
- 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
- 2017Opening the Black Box of Deep Neural Networks via Informationcited by 503
- 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 314
- 2017Estimating Mixture Entropy with Pairwise Distancescited by 36
- 2018Caveats for information bottleneck in deterministic scenarioscited by 34
- 2020How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networkscited by 32
- 2017Scalable Kernel K-Means Clustering with Nystrom Approximation: Relative-Error Boundscited by 16
- 2019Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi's Entropy and Tensor Kernelscited by 12
- 2017Nonparanormal Information Estimationcited by 4
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.