George Yiu

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2015-156

May 27, 2015

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-156.pdf

Machine learning results are often difficult to understand and draw insight from. While building a general machine learning pipeline, we design a user interface to help users of the system follow the machine learning process. This interface allows users to monitor the status of pipeline jobs as well as interactively explore results by inspecting individual samples and visualizing the impact of each feature that contributes to a sample's final classification.

Advisors: Anthony D. Joseph

---

BibTeX citation:

@mastersthesis{Yiu:EECS-2015-156,
    Author= {Yiu, George},
    Title= {Building a User Interface for a Temporal Machine Learning System},
    School= {EECS Department, University of California, Berkeley},
    Year= {2015},
    Month= {May},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-156.html},
    Number= {UCB/EECS-2015-156},
    Abstract= {Machine learning results are often difficult to understand and draw insight from. While building a general machine learning pipeline, we design a user interface to help users of the system follow the machine learning process. This interface allows users to monitor the status of pipeline jobs as well as interactively explore results by inspecting individual samples and visualizing the impact of each feature that contributes to a sample's final classification.},
}

EndNote citation:

%0 Thesis
%A Yiu, George 
%T Building a User Interface for a Temporal Machine Learning System
%I EECS Department, University of California, Berkeley
%D 2015
%8 May 27
%@ UCB/EECS-2015-156
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-156.html
%F Yiu:EECS-2015-156