What underlies rapid learning and systematic generalization in humans [article]

Andrew Joohun Nam, James L. McClelland
<span title="2021-07-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Despite the groundbreaking successes of neural networks, contemporary models require extensive training with massive datasets and exhibit poor out-of-sample generalization. One proposed solution is to build systematicity and domain-specific constraints into the model, echoing the tenets of classical, symbolic cognitive architectures. In this paper, we consider the limitations of this approach by examining human adults' ability to learn an abstract reasoning task from a brief instructional
more &raquo; ... al and explanatory feedback for incorrect responses, demonstrating that human learning dynamics and ability to generalize outside the range of the training examples differ drastically from those of a representative neural network model, and that the model is brittle to changes in features not anticipated by its authors. We present further evidence from human data that the ability to consistently solve the puzzles was associated with education, particularly basic mathematics education, and with the ability to provide a reliably identifiable, valid description of the strategy used. We propose that rapid learning and systematic generalization in humans may depend on a gradual, experience-dependent process of learning-to-learn using instructions and explanations to guide the construction of explicit abstract rules that support generalizable inferences.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.06994v1">arXiv:2107.06994v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kftryvz7jjhsdfziltqo2hbnp4">fatcat:kftryvz7jjhsdfziltqo2hbnp4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210719224214/https://arxiv.org/pdf/2107.06994v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ec/08/ec0895d0548be332fdc3cade898a8f37b9ca00f2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.06994v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>