Neural networks show surprising robustness to heavily corrupted inputs

Researchers have explored how neural networks can maintain accuracy even when presented with heavily corrupted input data. Their experiments with multi-layer perceptrons showed that networks could still perform well above chance when over 90% of the input was corrupted, far beyond human recognition. An analysis of infinite-width networks revealed that these networks implement a universal prototype rule, essentially assigning inputs to the class whose training-set average they most closely resemble, explaining this surprising robustness. AI

IMPACT Demonstrates a fundamental capability of neural networks to generalize from noisy data, potentially impacting how models are trained and deployed in real-world scenarios with imperfect data.

RANK_REASON Academic paper detailing a novel finding about model robustness. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Justin Tahmassebpur
• multi-layer perceptrons
• neural networks

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →