Publication

Supplementary Material - AL2: Progressive Activation Loss for Learning General Representations in Classification Neural Networks

Sabine Süsstrunk
2020
Working Papers

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.

Official source

https://infoscience.epfl.ch/entities/publication/ad113ad4-34da-4b7b-88fd-34f3e6cfc5a3

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Sabine Süsstrunk
2020
Working Papers

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/ad113ad4-34da-4b7b-88fd-34f3e6cfc5a3

About this result

Related concepts (32)

Artificial neural network

Artificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.

Convolutional neural network

Convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.

Types of artificial neural networks

There are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. Particularly, they are inspired by the behaviour of neurons and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research.

Related publications (32)

Supplementary Material - AL2: Progressive Activation Loss for Learning General Representations in Classification Neural Networks

Chat with Graph Search

Roadmap on Deep Learning for Microscopy

Towards a Theoretical Understanding of Efficiency and Bias in Deep Neural Networks

Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment