How deep is deep enough? -- Quantifying class separability in the hidden layers of deep neural networks

5 November 2018

Papers citing "How deep is deep enough? -- Quantifying class separability in the hidden layers of deep neural networks"

7 / 7 papers shown

Title
Classifying Overlapping Gaussian Mixtures in High Dimensions: From Optimal Classifiers to Neural Nets Khen Cohen Noam Levi Yaron Oz BDL 31 1 0 28 May 2024
SCHEME: Scalable Channel Mixer for Vision Transformers Deepak Sridhar Yunsheng Li Nuno Vasconcelos 33 0 0 01 Dec 2023
Quantifying the Variability Collapse of Neural Networks Jing-Xue Xu Haoxiong Liu 33 4 0 06 Jun 2023
Classification at the Accuracy Limit -- Facing the Problem of Data Ambiguity C. Metzner A. Schilling M. Traxdorf K. Tziridis Holger Schulze P. Krauss 17 11 0 04 Jun 2022
Neural Network based Successor Representations of Space and Language Paul Stoewer Christian Schlieker A. Schilling C. Metzner Andreas K. Maier P. Krauss 6 18 0 22 Feb 2022
A Novel Intrinsic Measure of Data Separability Shuyue Guan Murray H. Loew 13 14 0 11 Sep 2021
Softmax-based Classification is k-means Clustering: Formal Proof, Consequences for Adversarial Attacks, and Improvement through Centroid Based Tailoring Sibylle Hess W. Duivesteijn D. Mocanu 17 12 0 07 Jan 2020