On Human Intellect and Machine Failures: Troubleshooting Integrative Machine Learning Systems
THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, pp. 1017-1025, 2017.
We study the problem of troubleshooting machine learning systems that rely on analytical pipelines of distinct components. Understanding and fixing errors that arise in such integrative systems is difficult as failures can occur at multiple points in the execution workflow. Moreover, errors can propagate, become amplified or be suppressed...More
PPT (Upload PPT)