Analogical Reasoning Within a Conceptual Hyperspace

• URL: http://arxiv.org/abs/2411.08684v1
• Date: Wed, 13 Nov 2024 15:20:14 GMT
• Title: Analogical Reasoning Within a Conceptual Hyperspace
• Authors: Howard Goldowsky, Vasanth Sarathy,
• Abstract summary: We propose an approach to analogical inference that marries the neuro-symbolic computational power of hyperdimensional computing with Conceptual Spaces Theory. We present preliminary proof-of-concept experimental results within a toy domain and describe how it can perform category-based and property-based analogical reasoning.
• Score: 1.1049608786515839
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose an approach to analogical inference that marries the neuro-symbolic computational power of complex-sampled hyperdimensional computing (HDC) with Conceptual Spaces Theory (CST), a promising theory of semantic meaning. CST sketches, at an abstract level, approaches to analogical inference that go beyond the standard predicate-based structure mapping theories. But it does not describe how such an approach can be operationalized. We propose a concrete HDC-based architecture that computes several types of analogy classified by CST. We present preliminary proof-of-concept experimental results within a toy domain and describe how it can perform category-based and property-based analogical reasoning.

Related papers

• The Lattice Representation Hypothesis of Large Language Models [18.00499182102749]
  We show that linear attribute directions with separating thresholds induce a concept lattice via half-space intersections.<n>This geometry enables symbolic reasoning through geometric meet (intersection) and join (union) operations.
  arXiv  Detail & Related papers  (2026-03-01T18:42:59Z)
• Emergent Analogical Reasoning in Transformers [46.10175943435167]
  Despite its central role in cognition, the mechanisms by which Transformers acquire and implement analogical reasoning remain poorly understood.<n>We formalize analogical reasoning as the inference of correspondences between entities across categories.<n>We show that analogical reasoning in Transformers decomposes into two key components: geometric alignment of relational structure in the embedding space, and the application of a functor within the Transformer.
  arXiv  Detail & Related papers  (2026-02-02T11:49:36Z)
• A Geometric Unification of Concept Learning with Concept Cones [58.70836885177496]
  Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs) and Sparse Autoencoders (SAEs)<n>We show that both paradigms instantiate the same geometric structure.<n>CBMs provide human-defined reference geometries, while SAEs can be evaluated by how well their learned cones approximate or contain those of CBMs.
  arXiv  Detail & Related papers  (2025-12-08T09:51:46Z)
• Semantic Numeration Systems as Dynamical Systems [55.2480439325792]
  The cardinal abstract object (CAO) formed by them in a certain connectivity topology is proposed to be considered as a linear discrete dynamical system with nonlinear control.<n>The fundamental role of the configuration matrix, which combines information about the types of cardinal semantic operators in the CAO, their parameters and topology of connectivity, is demonstrated.
  arXiv  Detail & Related papers  (2025-07-28T19:29:36Z)
• Pretrained Embeddings as a Behavior Specification Mechanism [17.86560073144763]
  We introduce embeddings as a first-class construct in a specification language. We show that embedding-based specifications can be used to steer a system towards desirable behaviors.
  arXiv  Detail & Related papers  (2025-03-03T19:41:22Z)
• Coherent States in Gauge Theories: Topological Defects and Other Classical Configurations [0.0]
  We present a formulation of coherent states as of consistent quantum description of classical configurations. One of the key insights is the possibility of constructing the coherent states of pure-gauge configurations.
  arXiv  Detail & Related papers  (2024-11-18T15:35:57Z)
• 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)
• A Geometric Notion of Causal Probing [85.49839090913515]
  The linear subspace hypothesis states that, in a language model's representation space, all information about a concept such as verbal number is encoded in a linear subspace. We give a set of intrinsic criteria which characterize an ideal linear concept subspace. We find that, for at least one concept across two languages models, the concept subspace can be used to manipulate the concept value of the generated word with precision.
  arXiv  Detail & Related papers  (2023-07-27T17:57:57Z)
• 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)
• A Category-theoretical Meta-analysis of Definitions of Disentanglement [97.34033555407403]
  Disentangling the factors of variation in data is a fundamental concept in machine learning. This paper presents a meta-analysis of existing definitions of disentanglement.
  arXiv  Detail & Related papers  (2023-05-11T15:24:20Z)
• Compositional Probabilistic and Causal Inference using Tractable Circuit Models [20.07977560803858]
  We introduce md-vtrees, a novel structural formulation of (marginal) determinism in structured decomposable PCs. We derive the first polytime algorithms for causal inference queries such as backdoor adjustment on PCs.
  arXiv  Detail & Related papers  (2023-04-17T13:48:16Z)
• Concept Activation Regions: A Generalized Framework For Concept-Based Explanations [95.94432031144716]
  Existing methods assume that the examples illustrating a concept are mapped in a fixed direction of the deep neural network's latent space. In this work, we propose allowing concept examples to be scattered across different clusters in the DNN's latent space. This concept activation region (CAR) formalism yields global concept-based explanations and local concept-based feature importance.
  arXiv  Detail & Related papers  (2022-09-22T17:59:03Z)
• Quantum Simulation of Conformal Field Theory [77.34726150561087]
  We describe a quantum algorithm to simulate the dynamics of conformal field theories. A full analysis of the approximation errors suggests near-term applicability.
  arXiv  Detail & Related papers  (2021-09-29T06:44:33Z)
• A Neural Approach for Detecting Morphological Analogies [7.89271130004391]
  Analogical proportions are statements of the form "A is to B as C is to D" We propose a deep learning approach to detect morphological analogies.
  arXiv  Detail & Related papers  (2021-08-09T11:21:55Z)
• Formalising Concepts as Grounded Abstractions [68.24080871981869]
  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.
  arXiv  Detail & Related papers  (2021-01-13T15:22:01Z)
• Paraconsistent Foundations for Probabilistic Reasoning, Programming and Concept Formation [0.0]
  It is argued that 4-valued paraconsistent truth values (called here "p-bits") can serve as a conceptual, mathematical and practical foundation for highly AI-relevant forms of probabilistic logic and programming and concept formation. It is shown that appropriate averaging-across-situations and renormalization of 4-valued p-bits operating in accordance with Constructible Duality (CD) logic yields PLN (Probabilistic Logic Networks) strength-and-confidence truth values.
  arXiv  Detail & Related papers  (2020-12-28T20:14:49Z)
• Orthologics for Cones [5.994412766684843]
  In this paper we study logics for such geometric structures. We describe an extension of minimal orthologic with a partial modularity rule that holds for closed convex cones. This logic combines a feasible data structure (exploiting convexity/conicity) with sufficient expressivity, including full orthonegation.
  arXiv  Detail & Related papers  (2020-08-07T13:28:27Z)

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.