Algorithmic transparency
 | This article, Algorithmic transparency, has recently been created via the Articles for creation process. Please check to see if the reviewer has accidentally left this template after accepting the draft and take appropriate action as necessary.
Reviewer tools: Inform author |
Algorithmic transparency is the capacity for the user of an algorithm to understand its functioning and its resulting output. It is to be opposed to the functioning of an algorithm as a black box, which lacks explainability in its automated decision making.[1]
Current research around algorithmic transparency is mainly interested in the societal effects of accessing remote services running black box algorithms.[2] Some approaches propose ways to gain understanding about specific remote black box algorithms, by crafting inputs, via service APIs, and observing the resulting output.[3] [4]
See also
References
- ^ Diakopoulos, Nicholas (2015). "Algorithmic Accountability: Journalistic Investigation of Com- putational Power Structures". Digital Journalism. 3 (3): 398-415.
- ^ "Workshop on Data and Algorithmic Transparency". 2015. Retrieved 4 January 2017.
- ^ Tramèr, Florian; Zhang, Fan; Juels, Ari; K. Reiter, Michael; Ristenpart, Thomas (2016). "Stealing Machine Learning Models via Prediction APIs" (PDF). USENIX Security Symposium.
- ^ Le Merrer, Erwan; Trédan, Gilles (2017). "Uncovering Influence Cookbooks : Reverse Engineering the Topological Impact in Peer Ranking Services". Computer-Supported Cooperative Work and Social Computing.