Holographic Feature Representations Of Deep Networks
CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE (UAI2017)(2017)
摘要
It is often asserted that deep networks learn "features", traditionally expressed by the activations of intermediate nodes. We explore an alternative concept by defining features as partial derivatives of model output with respect to model parameters-extending a simple yet powerful idea from generalized linear models. The resulting features are not equivalent to node activations, and we show that they can induce a holographic representation of the complete model: the network's output on given data can be exactly replicated by a simple linear model over such features extracted from any ordered cut. We demonstrate useful advantages for this feature representation over standard representations based on node activations.
更多查看译文
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