Pragmatist Intelligence: Where the Principle of Usefulness Can Take ANNs

arXiv:2405.04386v1 Announce Type: cross
Abstract: Artificial neural networks (ANNs) perform extraordinarily on numerous tasks including classification or prediction, e.g., speech processing and image classification. These new functions are based on a computational model that is enabled to select freely all necessary internal model parameters as long as it eventually delivers the functionality it is supposed to exhibit. Here, we review the connection between the model parameter selection in machine learning (ML) algorithms running on ANNs and the epistemological theory of …

abstract anns artificial artificial neural networks arxiv classification computational cs.ai cs.lg eventually functions image intelligence networks neural networks parameters prediction processing speech speech processing tasks type