Unverified50% confidenceFactExact time
Geifman and El-Yaniv published "Selective Classification for Deep Neural Networks" at NeurIPS in 2017.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified2014 年 Yosinski 等人在论文《How transferable are features in deep neural networks?》中证明网络浅层学习的特征具有极高通用性，而深层特征逐渐变得任务特定66% similarUnverifiedExperiments by Zhang et al. (2017) demonstrated that standard deep neural networks can perfectly memorize training data with random labels, meaning that traditional generalization bounds based on model capacity completely break down.65% similarVerifiedDQN was proposed by DeepMind in 2013 and was the first to combine deep neural networks with Q-learning.65% similarUnverifiedModern recommendation systems primarily operate based on collaborative filtering and deep learning models, including Google's Wide & Deep and YouTube's deep neural network candidate generation model65% similarUnverified深度学习中CNN用于提取神经信号的空间特征，RNN/LSTM和Transformer架构用于捕捉时序依赖关系65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1004518API
curl https://kongchang.com/api/v1/knowledge/claims/1004518MCP
get_claim(id=1004518)