Unverified50% confidenceFactExact time
The concept of adversarial examples was first systematically proposed by Szegedy and other researchers in 2013.
1
Sources
50%
Confidence
Long-term
Relevance
9/14/2026
First Seen
Sources
Related Entities
Related Claims
Unverified对抗样本概念由Szegedy等人于2013年在论文《Intriguing properties of neural networks》中正式提出71% similarUnverifiedThe behavior of adversarial examples interfering with decision logic has precedents in traditional machine learning research.62% similarUnverifiedThe idea of embedding vectors can be traced back to Word2Vec proposed by Mikolov et al. in 2013, whose core assumption is the distributional hypothesis.61% similarUnverifiedFew-shot examples convey samples rather than rules, and the model's induction process is probabilistic with systematic biases, so examples and Schema should be used in conjunction rather than as substitutes for each other.61% similarUnverifiedExposure Bias问题最早由Samy Bengio等人于2015年在《Scheduled Sampling for Sequence Prediction》中系统描述61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/920661API
curl https://kongchang.com/api/v1/knowledge/claims/920661MCP
get_claim(id=920661)