Engineering Commons^™

Recurrent Network And Multi-Arm Bandit Methods For Multi-Task Learning Without Task Specification, Thy Nguyen, Tayo Obafemi-Ajayi

Electrical and Computer Engineering Faculty Research & Creative Works

This paper addresses the problem of multi-task learning (MTL) in settings where the task assignment is not known. We propose two mechanisms for the problem of inference of task's parameter without task specification: parameter adaptation and parameter selection methods. In parameter adaptation, the model's parameter is iteratively updated using a recurrent neural network (RNN) learner as the mechanism to adapt to different tasks. For the parameter selection model, a parameter matrix is learned beforehand with the task known apriori. During testing, a bandit algorithm is utilized to determine the appropriate parameter vector for the model on the fly. We explored …