Artificial Neural Nets and the Representation of Human Concepts

Timo Freiesleben
12/8/2023
cs.LGcs.AI

No confident code implementation found for this paper.

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 concepts to do so. However, evidence indicates that ANNs do not represent these concepts in individual units.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Are Concept Bottleneck Models Effective as Decision-Support Systems?

85% match2026

Psychology of Artificial Intelligence: Epistemological Markers of the Cognitive Analysis of Neural Networks

84% match2024

Whither symbols in the era of advanced neural networks?

84% match2025

Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks

84% match2022

A Brain-inspired Computational Model for Human-like Concept Learning

83% match2024

Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens

83% match2025

Cite this paper

@article{freiesleben2023artificial,
  title  = {Artificial Neural Nets and the Representation of Human Concepts},
  author = {Timo Freiesleben},
  year   = {2023},
  eprint = {2312.05337},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.05337v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.05337.svg)](https://codeofpaper.com/paper/2312.05337)

Discussion