File(s) under embargo

15

day(s)

until file(s) become available

TASK DETECTORS FOR PROGRESSIVE SYSTEMS

thesis
posted on 30.04.2021, 00:20 by Maxwell Joseph Jacobson
While methods like learning-without-forgetting [11] and elastic weight consolidation [22] accomplish high-quality transfer learning while mitigating catastrophic forgetting, progressive techniques such as Deepmind’s progressive neural network accomplish this while completely nullifying forgetting. However, progressive systems like this strictly require task labels during test time. In this paper, I introduce a novel task recognizer built from anomaly detection autoencoders that is capable of detecting the nature of the required task from input data.Alongside a progressive neural network or other progressive learning system, this task-aware network is capable of operating without task labels during run time while maintaining any catastrophic forgetting reduction measures implemented by the task model.

History

Degree Type

Master of Science

Department

Computer Science

Campus location

West Lafayette

Advisor/Supervisor/Committee Chair

Gustavo Rodriguez-Rivera

Additional Committee Member 2

Bruno Ribeiro

Additional Committee Member 3

Dan Goldwasser

Licence

Exports