Quantifying Nondeterminism and Inconsistency in Self-organizing Map Implementations
2021 IEEE International Conference on Artificial Intelligence Testing (AITest)（2021）
摘要
Self-organizing maps (SOMs) are a popular approach for neural network-based unsupervised learning. However the reliability of self-organizing map implementations has not been investigated. Using internal and external metrics, we define and check two basic SOM properties. First, determinism: a given SOM implementation should produce the same SOM when run repeatedly on the same training dataset. Sec...
更多查看译文
关键词
Self-organizing feature maps,Training,Measurement,Conferences,Neural networks,Reliability,Artificial intelligence
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要