Neural-Symbolic Integration: A Compositional Perspective

• URL: http://arxiv.org/abs/2010.11926v1
• Date: Thu, 22 Oct 2020 17:55:44 GMT
• Title: Neural-Symbolic Integration: A Compositional Perspective
• Abstract summary: The question of how to integrate a neural and a symbolic system in a emphcompositional manner remains open. Our work seeks to fill this gap by treating these two systems as black boxes to be integrated as modules into a single architecture. We are able to show that a symbolic module can be cleanly integrated with a neural module, and facilitate the latter's efficient training.
• Score: 8.566457170664926
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite significant progress in the development of neural-symbolic frameworks, the question of how to integrate a neural and a symbolic system in a \emph{compositional} manner remains open. Our work seeks to fill this gap by treating these two systems as black boxes to be integrated as modules into a single architecture, without making assumptions on their internal structure and semantics. Instead, we expect only that each module exposes certain methods for accessing the functions that the module implements: the symbolic module exposes a deduction method for computing the function's output on a given input, and an abduction method for computing the function's inputs for a given output; the neural module exposes a deduction method for computing the function's output on a given input, and an induction method for updating the function given input-output training instances. We are, then, able to show that a symbolic module -- with any choice for syntax and semantics, as long as the deduction and abduction methods are exposed -- can be cleanly integrated with a neural module, and facilitate the latter's efficient training, achieving empirical performance that exceeds that of previous work.

Related papers

• Self-explainable Operator Learning for Discovering Spatial Patterns in Functional Data [0.24554686192257422]
  Operator learning has emerged as a powerful tool for modeling complex physical systems in functional spaces.<n>We introduce a self-explainable operator learning framework that overcomes this challenge by reformulating operator learning as a linear combination of generalized functional linear models.<n>We demonstrate the framework on function-to-scalar and function-to-function mappings in fluid flow problems involving blood flow and unsteady aerodynamics.
  arXiv  Detail & Related papers  (2026-07-02T14:11:20Z)
• Modular Neural Computer [0.0]
  The Modular Neural Computer (MNC) is a memory-augmented neural architecture for exact computation on variable-length inputs.<n>The architecture is illustrated through three case studies: computing the minimum of an array, sorting an array in place, and executing A* search on a fixed problem instance.
  arXiv  Detail & Related papers  (2026-03-04T16:29:20Z)
• Modular Machine Learning with Applications to Genetic Circuit Composition [0.0]
  Learning the modules' input/output functions is also necessary for designing new systems from different composition architectures.<n>We propose a modular learning framework, which incorporates prior knowledge of the system's compositional structure to identify the composing modules' input/output functions.<n>By reducing the need for experimental data and allowing module identification, this framework offers the potential to ease the design of synthetic biological circuits.
  arXiv  Detail & Related papers  (2025-09-23T21:49:13Z)
• Semialgebraic Neural Networks: From roots to representations [6.259381563339797]
  We introduce Semialgebraic Networks (SANNs), a neural network architecture capable of representing any bounded semialgebraic function. We show by construction that the SANN architecture is able to execute this continuation method, thus evaluating the learned semialgebraic function. We provide example applications of these networks and show they can be trained with traditional deep-learning techniques.
  arXiv  Detail & Related papers  (2025-01-02T22:52:07Z)
• A Computational Model of Learning and Memory Using Structurally Dynamic Cellular Automata [0.0]
  This paper proposes a mathematical and computational model of learning and memory based on a small set of bio-plausible functions. Experimental results show that the model can make near-optimal choices to re-discover a reward state after a single training run.
  arXiv  Detail & Related papers  (2024-12-20T17:26:17Z)
• A Resolution Independent Neural Operator [0.0]
  We introduce a general framework for operator learning from input-output data with arbitrary sensor locations and counts. We propose two dictionary learning algorithms that adaptively learn continuous basis functions, parameterized as implicit neural representations. These basis functions project input function data onto a finite-dimensional embedding space, making it compatible with DeepONet without architectural changes.
  arXiv  Detail & Related papers  (2024-07-17T21:03:21Z)
• stl2vec: Semantic and Interpretable Vector Representation of Temporal Logic [0.5956301166481089]
  We propose a semantically grounded vector representation (feature embedding) of logic formulae. We compute continuous embeddings of formulae with several desirable properties. We demonstrate the efficacy of the approach in two tasks: learning model checking and neurosymbolic framework.
  arXiv  Detail & Related papers  (2024-05-23T10:04:56Z)
• FIND: A Function Description Benchmark for Evaluating Interpretability Methods [86.80718559904854]
  This paper introduces FIND (Function INterpretation and Description), a benchmark suite for evaluating automated interpretability methods. FIND contains functions that resemble components of trained neural networks, and accompanying descriptions of the kind we seek to generate. We evaluate methods that use pretrained language models to produce descriptions of function behavior in natural language and code.
  arXiv  Detail & Related papers  (2023-09-07T17:47:26Z)
• 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)
• Unification of popular artificial neural network activation functions [0.0]
  We present a unified representation of the most popular neural network activation functions. Adopting Mittag-Leffler functions of fractional calculus, we propose a flexible and compact functional form.
  arXiv  Detail & Related papers  (2023-02-21T21:20:59Z)
• A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms [64.3064050603721]
  We generalize Runge-Kutta neural network to a recurrent neural network (R2N2) superstructure for the design of customized iterative algorithms. We demonstrate that regular training of the weight parameters inside the proposed superstructure on input/output data of various computational problem classes yields similar iterations to Krylov solvers for linear equation systems, Newton-Krylov solvers for nonlinear equation systems, and Runge-Kutta solvers for ordinary differential equations.
  arXiv  Detail & Related papers  (2022-11-22T16:30:33Z)
• Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection [50.14730810124592]
  Submodular functions and variants, through their ability to characterize diversity and coverage, have emerged as a key tool for data selection and summarization. We propose FLEXSUBNET, a family of flexible neural models for both monotone and non-monotone submodular functions.
  arXiv  Detail & Related papers  (2022-10-20T06:00:45Z)
• Neural Network Module Decomposition and Recomposition [35.21448933547118]
  We propose a modularization method that decomposes a deep neural network (DNN) into small modules from a functionality perspective. We demonstrate that the proposed method can decompose and recompose DNNs with high compression ratio and high accuracy.
  arXiv  Detail & Related papers  (2021-12-25T08:36:47Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers [84.57980167400513]
  Neural Function Modules (NFM) aims to introduce the same structural capability into deep learning. Most of the work in the context of feed-forward networks combining top-down and bottom-up feedback is limited to classification problems. The key contribution of our work is to combine attention, sparsity, top-down and bottom-up feedback, in a flexible algorithm.
  arXiv  Detail & Related papers  (2020-10-15T20:43:17Z)

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.