On the Intrinsic Limits to Representationally-Adaptive Machine-Learning

Abstract

Online learning is a familiar problem setting within Machine-Learning in which data is presented serially in time to a learning agent, requiring it to progressively adapt within the constraints of the learning algorithm. More sophisticated variants may involve concepts such as transfer-learning which increase this adaptive capability, enhancing the learner's cognitive capacities in a manner that can begin to imitate the open-ended learning capabilities of human beings. We shall argue in this paper, however, that a full realization of this notion requires that, in addition to the capacity to adapt to novel data, autonomous online learning must ultimately incorporate the capacity to update its own representational capabilities in relation to the data. We therefore enquire about the philosophical limits of this process, and argue that only fully embodied learners exhibiting an a priori perception-action link in order to ground representational adaptations are capable of exhibiting the full range of human cognitive capability.