Timezone: »

System-wide Monitoring Architectures with Explanations
Leilani Gilpin

Fri Jul 17 05:55 AM -- 06:40 AM (PDT) @
Event URL: https://slideslive.com/s/leilani-h-gilpin-37394 »

I present a new architecture for detecting and explaining complex system failures. My contribution is a system-wide monitoring architecture, which is composed of introspective, overlapping committees of subsystems. Each subsystem is encapsulated in a "reasonableness" monitor, an adaptable framework that supplements local decisions with commonsense data and reasonableness rules. This framework is dynamic and introspective: it allows each subsystem to defend its decisions in different contexts--to the committees it participates in and to itself.

For reconciling system-wide errors, I developed a comprehensive architecture that I call "Anomaly Detection through Explanations" (ADE). The ADE architecture contributes an explanation synthesizer that produces an argument tree, which in turn can be traced and queried to determine the support of a decision, and to construct counterfactual explanations. I have applied this methodology to detect incorrect labels in semi-autonomous vehicle data, and to reconcile inconsistencies in simulated anomalous driving scenarios.

In conclusion, I discuss the difficulties in /evaluating/ these types of monitoring systems. I argue that meaningful evaluation tasks should be dynamic: designing collaborative tasks (between a human and machine) that require /explanations/ for success.

Author Information

Leilani Gilpin (MIT)

More from the Same Authors

  • 2020 : Panel discussion »
    Neil Lawrence · Mohammad Ghavamzadeh · Leilani Gilpin · Huyen Nguyen · Ernest Mwebaze · Nevena Lalic