Transcription of Axiomatic Attribution for Deep Networks
{{id}} {{{paragraph}}}
Example: confidence
Axiomatic Attribution for Deep Networks
Axiomatic Attribution for Deep Networks Mukund Sundararajan * 1 Ankur Taly * 1 Qiqi Yan * 1. Abstract Shrikumar et al., 2016; Binder et al., 2016; Springenberg et al., 2014). We study the problem of attributing the pre- diction of a deep network to its input features, The intention of these works is to understand the input- [ ] 13 Jun 2017. a problem previously studied by several other output behavior of the deep network, which gives us the works. We identify two fundamental axioms ability to improve it. Such understandability is critical to Sensitivity and Implementation Invariance that all computer programs, including machine learning mod- Attribution methods ought to satisfy. We show els. There are also other applications of Attribution . They that they are not satisfied by most known attri- could be used within a product driven by machine learn- bution methods, which we consider to be a fun- ing to provide a rationale for the recommendation. For in- damental weakness of those methods.
they break sensitivity, a property that all attribution meth-ods should satisfy. 2.1. Axiom: Sensitivity(a) An attribution method satisfies Sensitivity(a) if for every input and baseline that differ in one feature but have differ-ent predictions then the differing feature should be given a non-zero attribution. (Later in the paper, we will have a
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: