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 a constant improvement in the network architectures and trainingmethodologies, Neural Networks (NNs) are increasingly being deployed inreal-world Machine Learning systems. However, despite their impressiveperformance on "known inputs", these NNs can fail absurdly on the "unseeninputs", especially if these real-time inputs deviate from the training datasetdistributions, or contain certain types of input noise. This indicates the lownoise tolerance of NNs, which is a major reason for the recent increase ofadversarial attacks. This is a serious concern, particularly forsafety-critical applications, where inaccurate results lead to direconsequences. We propose a novel methodology that leverages model checking forthe Formal Analysis of Neural Network (FANNet) under different input noiseranges. Our methodology allows us to rigorously analyze the noise tolerance ofNNs, their input node sensitivity, and the effects of training bias on theirperformance, e.g., in terms of classification accuracy. For evaluation, we usea feed-forward fully-connected NN architecture trained for the Leukemiaclassification. Our experimental results show $\pm 11\%$ noise tolerance forthe given trained network, identify the most sensitive input nodes, and confirmthe biasness of the available training dataset.

FANNet: Formal Analysis of Noise Tolerance, Training Bias and Input Sensitivity in Neural Networks