Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases

• URL: http://arxiv.org/abs/2102.11965v1
• Date: Tue, 23 Feb 2021 22:16:05 GMT
• Title: Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases
• Abstract summary: unification of statistical (data-driven) and symbolic (knowledge-driven) methods is one of the key challenges of modern AI. Recent years have seen large number of publications on such hybrid neuro-symbolic AI systems. We propose a set of modular design patterns for such hybrid, neuro-symbolic systems.
• Score: 0.3849857432787594
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is widely recognised as one of the key challenges of modern AI. Recent years have seen large number of publications on such hybrid neuro-symbolic AI systems. That rapidly growing literature is highly diverse and mostly empirical, and is lacking a unifying view of the large variety of these hybrid systems. In this paper we analyse a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems. We are able to describe the architecture of a very large number of hybrid systems by composing only a small set of elementary patterns as building blocks. The main contributions of this paper are: 1) a taxonomically organised vocabulary to describe both processes and data structures used in hybrid systems; 2) a set of 15+ design patterns for hybrid AI systems, organised in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems. Our patterns reveal similarities between systems that were not recognised until now. Finally, our design patterns extend and refine Kautz' earlier attempt at categorising neuro-symbolic architectures.

Related papers

• Agentic Design Patterns: A System-Theoretic Framework [8.108572809924956]
  Existing efforts to agentic design patterns often lack a rigorous systems-theoretic foundation.<n>We propose a novel system-theoretic framework that deconstructs an agentic AI system into five core, interacting functional subsystems.<n>We present a collection of 12 agentic design patterns that offer reusable, structural solutions to recurring problems in agent design.
  arXiv  Detail & Related papers  (2026-01-27T16:14:08Z)
• Bidirectional Representations Augmented Autoregressive Biological Sequence Generation:Application in De Novo Peptide Sequencing [51.12821379640881]
  Autoregressive (AR) models offer holistic, bidirectional representations but face challenges with generative coherence and scalability.<n>We propose a hybrid framework enhancing AR generation by dynamically integrating rich contextual information from non-autoregressive mechanisms.<n>A novel cross-decoder attention module enables the AR decoder to iteratively query and integrate these bidirectional features.
  arXiv  Detail & Related papers  (2025-10-09T12:52:55Z)
• Learning neuro-symbolic convergent term rewriting systems [47.129504708849446]
  We introduce a general framework for learning convergent term rewriting systems using a neuro-symbolic architecture inspired by the rewriting algorithm itself.<n>We present two modular implementations of such architecture: the Neural Rewriting System (NRS) and the Fast Neural Rewriting System (FastNRS)
  arXiv  Detail & Related papers  (2025-07-25T15:24:56Z)
• Broad Spectrum Structure Discovery in Large-Scale Higher-Order Networks [1.7273380623090848]
  We introduce a class of probabilistic models that efficiently represents and discovers a broad spectrum of mesoscale structure in large-scale hypergraphs.<n>By modeling observed node interactions through latent interactions among classes using low-rank representations, our approach tractably captures rich structural patterns.<n>Our model improves link prediction over state-of-the-art methods and discovers interpretable structures in diverse real-world systems.
  arXiv  Detail & Related papers  (2025-05-27T20:34:58Z)
• Applying Cognitive Design Patterns to General LLM Agents [4.055489363682198]
  This paper outlines a few recurring cognitive design patterns that have appeared in various pre-transformer AI architectures.<n>We then explore how these patterns are evident in systems using large language models (LLMs)<n>Examining and applying these recurring patterns enables predictions of gaps or deficiencies in today's Agentic LLM Systems.
  arXiv  Detail & Related papers  (2025-05-11T18:29:54Z)
• Learning System Dynamics without Forgetting [60.08612207170659]
  Predicting trajectories of systems with unknown dynamics is crucial in various research fields, including physics and biology. We present a novel framework of Mode-switching Graph ODE (MS-GODE), which can continually learn varying dynamics. We construct a novel benchmark of biological dynamic systems, featuring diverse systems with disparate dynamics.
  arXiv  Detail & Related papers  (2024-06-30T14:55:18Z)
• Learnable & Interpretable Model Combination in Dynamic Systems Modeling [0.0]
  We discuss which types of models are usually combined and propose a model interface that is capable of expressing a variety of mixed equation based models. We propose a new wildcard topology, that is capable of describing the generic connection between two combined models in an easy to interpret fashion. The contributions of this paper are highlighted at a proof of concept: Different connection topologies between two models are learned, interpreted and compared.
  arXiv  Detail & Related papers  (2024-06-12T11:17:11Z)
• Hybrid Modeling Design Patterns [10.266928164137635]
  We provide four base patterns that can serve as blueprints for combining data-driven components with domain knowledge into a hybrid approach. We also present two composition patterns that govern the combination of the base patterns into more complex hybrid models. Each design pattern is illustrated by typical use cases from application areas such as climate modeling, engineering, and physics.
  arXiv  Detail & Related papers  (2023-12-29T15:40:38Z)
• Design Patterns for AI-based Systems: A Multivocal Literature Review and Pattern Repository [6.184279908456794]
  This study provides an overview of design patterns for AI-based systems, both new and adapted ones. New patterns for AI-based systems are emerging, but existing patterns have also been adapted to this new context. Our results can be used by researchers as a foundation for follow-up studies and by practitioners to discover relevant patterns for informing the design of AI-based systems.
  arXiv  Detail & Related papers  (2023-03-23T10:57:11Z)
• AI-Empowered Hybrid MIMO Beamforming [85.48860461696417]
  Hybrid multiple-input multiple-output (MIMO) systems implement part of their beamforming in analog and part in digital. Recent years have witnessed a growing interest in using data-aided artificial intelligence (AI) tools for hybrid beamforming design. This article reviews candidate strategies to leverage data to improve real-time hybrid beamforming design.
  arXiv  Detail & Related papers  (2023-03-03T06:04:20Z)
• Constructing Neural Network-Based Models for Simulating Dynamical Systems [59.0861954179401]
  Data-driven modeling is an alternative paradigm that seeks to learn an approximation of the dynamics of a system using observations of the true system. This paper provides a survey of the different ways to construct models of dynamical systems using neural networks. In addition to the basic overview, we review the related literature and outline the most significant challenges from numerical simulations that this modeling paradigm must overcome.
  arXiv  Detail & Related papers  (2021-11-02T10:51:42Z)
• Modular Design Patterns for Hybrid Actors [0.0]
  This paper is an extension of the boxology to describe distributed hybrid AI systems with actors and interactions. We show examples using a few design patterns relevant in multi-agent systems and human-agent interaction in general and, specifically, in the manufacturing domain.
  arXiv  Detail & Related papers  (2021-09-20T07:19:54Z)
• Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning [49.6928533575956]
  We use neural inference to mediate between the neural System 1 and the logical System 2. Results in robust story generation and grounded instruction-following show that this approach can increase the coherence and accuracy of neurally-based generations.
  arXiv  Detail & Related papers  (2021-07-06T17:59:49Z)
• Towards a Predictive Processing Implementation of the Common Model of Cognition [79.63867412771461]
  We describe an implementation of the common model of cognition grounded in neural generative coding and holographic associative memory. The proposed system creates the groundwork for developing agents that learn continually from diverse tasks as well as model human performance at larger scales.
  arXiv  Detail & Related papers  (2021-05-15T22:55:23Z)
• Scholarly AI system diagrams as an access point to mental models [6.233820957059352]
  Complex systems, such as Artificial Intelligence (AI) systems, are comprised of many interrelated components. In order to represent these systems, demonstrating the relations between components is essential. Diagrams, as "icons of relation", are a prevalent medium for signifying complex systems.
  arXiv  Detail & Related papers  (2021-04-30T07:55:18Z)
• Model-Based Deep Learning [155.063817656602]
  Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques. Deep neural networks (DNNs) use generic architectures which learn to operate from data, and demonstrate excellent performance. We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches.
  arXiv  Detail & Related papers  (2020-12-15T16:29:49Z)
• Automated and Formal Synthesis of Neural Barrier Certificates for Dynamical Models [70.70479436076238]
  We introduce an automated, formal, counterexample-based approach to synthesise Barrier Certificates (BC) The approach is underpinned by an inductive framework, which manipulates a candidate BC structured as a neural network, and a sound verifier, which either certifies the candidate's validity or generates counter-examples. The outcomes show that we can synthesise sound BCs up to two orders of magnitude faster, with in particular a stark speedup on the verification engine.
  arXiv  Detail & Related papers  (2020-07-07T07:39:42Z)

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.