English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Despite their effective use in various fields, many aspects of neuralnetworks are poorly understood. One important way to investigate thecharacteristics of neural networks is to explore the loss landscape. However,most models produce a high-dimensional non-convex landscape which is difficultto visualize. We discuss and extend existing visualization methods based on 1D-and 2D slicing with a novel method that approximates the actual loss landscapegeometry by using charts with interpretable axes. Based on the assumption thatobservations on small neural networks can generalize to more complex systemsand provide us with helpful insights, we focus on small models in the range ofa few dozen weights, which enables computationally cheap experiments and theuse of an interactive dashboard. We observe symmetries around the zero vector,the influence of different layers on the global landscape, the different weightsensitivities around a minimizer, and how gradient descent navigates high-lossobstacles. The user study resulted in an average SUS (System Usability Scale)score with suggestions for improvement and opened up a number of possibleapplication scenarios, such as autoencoders and ensemble networks.

FuNNscope: Visual microscope for interactively exploring the loss landscape of fully connected neural networks