An Information Theoretic Interpretation to Deep Neural Networks

May 16, 2019 Β· Declared Dead Β· πŸ› International Symposium on Information Theory

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Shao-Lun Huang, Xiangxiang Xu, Lizhong Zheng, Gregory W. Wornell arXiv ID 1905.06600 Category cs.IT: Information Theory Cross-listed cs.LG Citations 46 Venue International Symposium on Information Theory Last Checked 6 months ago
Abstract
It is commonly believed that the hidden layers of deep neural networks (DNNs) attempt to extract informative features for learning tasks. In this paper, we formalize this intuition by showing that the features extracted by DNN coincide with the result of an optimization problem, which we call the `universal feature selection' problem, in a local analysis regime. We interpret the weights training in DNN as the projection of feature functions between feature spaces, specified by the network structure. Our formulation has direct operational meaning in terms of the performance for inference tasks, and gives interpretations to the internal computation results of DNNs. Results of numerical experiments are provided to support the analysis.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Information Theory

Died the same way β€” πŸ‘» Ghosted