Artificial Neural Nets and the Representation of Human Concepts

arXiv:2312.05337v2 Announce Type: replace
Abstract: What do artificial neural networks (ANNs) learn? The machine learning (ML) community shares the narrative that ANNs must develop abstract human concepts to perform complex tasks. Some go even further and believe that these concepts are stored in individual units of the network. Based on current research, I systematically investigate the assumptions underlying this narrative. I conclude that ANNs are indeed capable of performing complex prediction tasks, and that they may learn human and non-human …

abstract anns artificial artificial neural networks arxiv community concepts cs.ai cs.lg current human learn machine machine learning narrative network networks neural nets neural networks representation shares tasks type units