Supplementary Material - AL2: Progressive Activation Loss for Learning General Representations in Classification Neural Networks
El Helou, Majed; Dümbgen, Frederike; Süsstrunk, Sabine
2020

Files

Abstract

In this supplementary material, we present the details of the neural network architecture and training settings used in all our experiments. This holds for all experiments presented in the main paper as well as in this supplementary material. We also show the summary results of all of our 96 experiments (test accuracy, training cross-entropy loss, and regularization loss), sampled at 100 epoch intervals. We analyze these results for each of the benchmark datasets, namely MNIST, Fashion-MNIST and CIFAR10, and underline global observations we make throughout the entire experiment set.

Details

Title Supplementary Material - AL2: Progressive Activation Loss for Learning General Representations in Classification Neural Networks
Author(s) El Helou, Majed ; Dümbgen, Frederike ; Süsstrunk, Sabine
Pagination 8
Date 2020
Publisher ICASSP
Laboratories IVRL
LCAV
Record Appears in Scientific production and competences > I&C - School of Computer and Communication Sciences > IINFCOM > IVRL - Image and Visual Representation Laboratory
Scientific production and competences > I&C - School of Computer and Communication Sciences > IINFCOM > LCAV - Audio Visual Communications Laboratory
Scientific production and competences > Euler Center for Signal Processing
Working papers
Work produced at EPFL
Submitted
Record creation date 2019-10-21

Actions

Preview