Computer Science > Artificial Intelligence
[Submitted on 12 Sep 2023 (v1), last revised 1 May 2024 (this version, v5)]
Title:The Relational Bottleneck as an Inductive Bias for Efficient Abstraction
View PDF HTML (experimental)Abstract:A central challenge for cognitive science is to explain how abstract concepts are acquired from limited experience. This has often been framed in terms of a dichotomy between connectionist and symbolic cognitive models. Here, we highlight a recently emerging line of work that suggests a novel reconciliation of these approaches, by exploiting an inductive bias that we term the relational bottleneck. In that approach, neural networks are constrained via their architecture to focus on relations between perceptual inputs, rather than the attributes of individual inputs. We review a family of models that employ this approach to induce abstractions in a data-efficient manner, emphasizing their potential as candidate models for the acquisition of abstract concepts in the human mind and brain.
Submission history
From: Taylor Webb [view email][v1] Tue, 12 Sep 2023 22:44:14 UTC (1,752 KB)
[v2] Sat, 20 Jan 2024 04:56:17 UTC (2,096 KB)
[v3] Thu, 28 Mar 2024 18:18:08 UTC (2,096 KB)
[v4] Thu, 4 Apr 2024 18:08:52 UTC (2,096 KB)
[v5] Wed, 1 May 2024 05:36:30 UTC (2,096 KB)
References & Citations
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.