Formalising Concepts as Grounded Abstractions
- URL: http://arxiv.org/abs/2101.05125v1
- Date: Wed, 13 Jan 2021 15:22:01 GMT
- Title: Formalising Concepts as Grounded Abstractions
- Authors: Stephen Clark, Alexander Lerchner, Tamara von Glehn, Olivier Tieleman,
Richard Tanburn, Misha Dashevskiy, Matko Bosnjak
- Abstract summary: This report shows how representation learning can be used to induce concepts from raw data.
The main technical goal of this report is to show how techniques from representation learning can be married with a lattice-theoretic formulation of conceptual spaces.
- Score: 68.24080871981869
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The notion of concept has been studied for centuries, by philosophers,
linguists, cognitive scientists, and researchers in artificial intelligence
(Margolis & Laurence, 1999). There is a large literature on formal,
mathematical models of concepts, including a whole sub-field of AI -- Formal
Concept Analysis -- devoted to this topic (Ganter & Obiedkov, 2016). Recently,
researchers in machine learning have begun to investigate how methods from
representation learning can be used to induce concepts from raw perceptual data
(Higgins, Sonnerat, et al., 2018). The goal of this report is to provide a
formal account of concepts which is compatible with this latest work in deep
learning.
The main technical goal of this report is to show how techniques from
representation learning can be married with a lattice-theoretic formulation of
conceptual spaces. The mathematics of partial orders and lattices is a standard
tool for modelling conceptual spaces (Ch.2, Mitchell (1997), Ganter and
Obiedkov (2016)); however, there is no formal work that we are aware of which
defines a conceptual lattice on top of a representation that is induced using
unsupervised deep learning (Goodfellow et al., 2016). The advantages of
partially-ordered lattice structures are that these provide natural mechanisms
for use in concept discovery algorithms, through the meets and joins of the
lattice.
Related papers
- What Machine Learning Tells Us About the Mathematical Structure of Concepts [0.0]
The study highlights how each framework provides a distinct mathematical perspective for modeling concepts.
This work emphasizes the importance of interdisciplinary dialogue, aiming to enrich our understanding of the complex relationship between human cognition and artificial intelligence.
arXiv Detail & Related papers (2024-08-28T03:30:22Z) - Learning Discrete Concepts in Latent Hierarchical Models [73.01229236386148]
Learning concepts from natural high-dimensional data holds potential in building human-aligned and interpretable machine learning models.
We formalize concepts as discrete latent causal variables that are related via a hierarchical causal model.
We substantiate our theoretical claims with synthetic data experiments.
arXiv Detail & Related papers (2024-06-01T18:01:03Z) - Learning Interpretable Concepts: Unifying Causal Representation Learning
and Foundation Models [51.43538150982291]
We study how to learn human-interpretable concepts from data.
Weaving together ideas from both fields, we show that concepts can be provably recovered from diverse data.
arXiv Detail & Related papers (2024-02-14T15:23:59Z) - ConcEPT: Concept-Enhanced Pre-Training for Language Models [57.778895980999124]
ConcEPT aims to infuse conceptual knowledge into pre-trained language models.
It exploits external entity concept prediction to predict the concepts of entities mentioned in the pre-training contexts.
Results of experiments show that ConcEPT gains improved conceptual knowledge with concept-enhanced pre-training.
arXiv Detail & Related papers (2024-01-11T05:05:01Z) - Pregeometry, Formal Language and Constructivist Foundations of Physics [0.0]
We discuss the metaphysics of pregeometric structures, upon which new and existing notions of quantum geometry may find a foundation.
We draw attention to evidence suggesting that the framework of formal language, in particular, homotopy type theory, provides the conceptual building blocks for a theory of pregeometry.
arXiv Detail & Related papers (2023-11-07T13:19:29Z) - A Recursive Bateson-Inspired Model for the Generation of Semantic Formal
Concepts from Spatial Sensory Data [77.34726150561087]
This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex sensory data.
The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept.
The model is able to produce fairly rich yet human-readable conceptual representations without training.
arXiv Detail & Related papers (2023-07-16T15:59:13Z) - ConceptX: A Framework for Latent Concept Analysis [21.760620298330235]
We present ConceptX, a human-in-the-loop framework for interpreting and annotating latent representational space in Language Models (pLMs)
We use an unsupervised method to discover concepts learned in these models and enable a graphical interface for humans to generate explanations for the concepts.
arXiv Detail & Related papers (2022-11-12T11:31:09Z) - Human-Centered Concept Explanations for Neural Networks [47.71169918421306]
We introduce concept explanations including the class of Concept Activation Vectors (CAV)
We then discuss approaches to automatically extract concepts, and approaches to address some of their caveats.
Finally, we discuss some case studies that showcase the utility of such concept-based explanations in synthetic settings and real world applications.
arXiv Detail & Related papers (2022-02-25T01:27:31Z) - Artificial Cognitively-inspired Generation of the Notion of Topological
Group in the Context of Artificial Mathematical Intelligence [0.0]
We provide the explicit artificial generation (or conceptual computation) for the fundamental mathematical notion of topological groups.
The concept of topological groups is explicitly generated through three different artificial specifications.
arXiv Detail & Related papers (2021-12-05T01:39:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.