The Authority of "Fair" in Machine Learning
Author:
Michael Skirpan, Department of Computer Science, University of Colorado Boulder
Abstract:
In this paper, we argue for the adoption of a normative definition of fairness within the machine learning community. After characterizing this definition, we review the current literature of Fair ML in light of its implications. We end by suggesting ways to incorporate a broader community and generate further debate around how to decide what is fair in ML.
More on http://www.kdd.org/kdd2017/
KDD2017 Conference is published on http://videolectures.net/
Видео The Authority of "Fair" in Machine Learning канала KDD2017 video
Michael Skirpan, Department of Computer Science, University of Colorado Boulder
Abstract:
In this paper, we argue for the adoption of a normative definition of fairness within the machine learning community. After characterizing this definition, we review the current literature of Fair ML in light of its implications. We end by suggesting ways to incorporate a broader community and generate further debate around how to decide what is fair in ML.
More on http://www.kdd.org/kdd2017/
KDD2017 Conference is published on http://videolectures.net/
Видео The Authority of "Fair" in Machine Learning канала KDD2017 video
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Designing AI at Scale to Power Everyday Life
Estimation of Recent Ancestral Origins of Individuals on a Large Scale
struc2vec: Learning Node Representations from Structural Identity
Learning to Generate Rock Descriptions from Multivariate Well Logs with Hierarchical Attention
A Local Algorithm for StructurePreserving Graph Cut
EmbedJoin: Efficient Edit Similarity Joins via Embeddings
Multi-Aspect Streaming Tensor Completion
Planning Bike Lanes based on SharingBikes' Trajectories
Tripoles: A New Class of Relationships in Time Series Data
Industrial Machine Learning
Optimal Reserve Price for Online Ads Trading Based on Inventory Identification
Multi-Aspect Streaming Tensor Completion
Dispatch with Confidence: Integration of machine learning
Learning certifiably optimal rule lists for categorical data
Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking
HinDroid: An Intelligent Android Malware Detection System
Revisiting power-law distributions in spectra of real world networks
KDD Business Lunch
Traffic sensor health monitoring using spatiotemporal graphical modeling
A Practical Algorithm for Solving the Incoherence Problem of Topic Models In Industrial Applications
Detecting Network Effects: Randomizing Over Randomized Experiments