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

With the recent success of deep neural networks in computer vision, it isimportant to understand the internal working of these networks. What does agiven neuron represent? The concepts captured by a neuron may be hard tounderstand or express in simple terms. The approach we propose in this paper isto characterize the region of input space that excites a given neuron to acertain level; we call this the inverse set. This inverse set is a complicatedhigh dimensional object that we explore by an optimization-based samplingapproach. Inspection of samples of this set by a human can reveal regularitiesthat help to understand the neuron. This goes beyond approaches which werelimited to finding an image which maximally activates the neuron or usingMarkov chain Monte Carlo to sample images, but this is very slow, generatessamples with little diversity and lacks control over the activation value ofthe generated samples. Our approach also allows us to explore the intersectionof inverse sets of several neurons and other variations.

Sampling the "Inverse Set" of a Neuron: An Approach to Understanding Neural Nets