Understanding activation patterns in artificial neural networks by exploring stochastic processes: Discriminating generalization from memorization
Authors:
- Stephan Johann LehmlerSLStephan Johann Lehmler
- Muhammad Saif-Ur-RehmanMSMuhammad Saif-Ur-Rehman
- Tobias GlasmachersTGTobias Glasmachers
- Ioannis IossifidisIIIoannis Iossifidis
Open Access
- 19 September 2024
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 610
Abstract
No abstract availableKeywords
This publication has 33 references indexed in Scilit:
- Accelerating CNN Training by Pruning Activation Gradients2020
- Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothnessNeural Networks, 2020
- Activity-dependent neuron model for noise resistanceNeurocomputing, 2019
- Doubly stochastic radial basis function methodsJournal of Computational Physics, 2018
- Multiscale analysis of neural spike trainsStatistics in Medicine, 2013
- Drawing inferences from Fano factor calculationsJournal of Neuroscience Methods, 2010
- Beyond Poisson: Increased Spike-Time Regularity across Primate Parietal CortexNeuron, 2009
- Dynamics of stochastic artificial neuronsNeurocomputing, 2001
- The structure and precision of retinal spike trainsProceedings of the National Academy of Sciences, 1997
- Noise, neural codes and cortical organizationCurrent Opinion in Neurobiology, 1994