Neurosymbolic Deep Learning Semantics

• URL: http://arxiv.org/abs/2511.02825v1
• Date: Tue, 04 Nov 2025 18:51:04 GMT
• Title: Neurosymbolic Deep Learning Semantics
• Authors: Artur d'Avila Garcez, Simon Odense,
• Abstract summary: We use logic in a neurosymbolic framework to offer a much needed semantics for deep learning.<n>Deep learning and neurosymbolic AI lack a general set of conditions to ensure that desirable properties are satisfied.<n>We introduce a framework for semantic encoding, making explicit the mapping between neural networks and logic.
• Score: 0.02291770711277359
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Artificial Intelligence (AI) is a powerful new language of science as evidenced by recent Nobel Prizes in chemistry and physics that recognized contributions to AI applied to those areas. Yet, this new language lacks semantics, which makes AI's scientific discoveries unsatisfactory at best. With the purpose of uncovering new facts but also improving our understanding of the world, AI-based science requires formalization through a framework capable of translating insight into comprehensible scientific knowledge. In this paper, we argue that logic offers an adequate framework. In particular, we use logic in a neurosymbolic framework to offer a much needed semantics for deep learning, the neural network-based technology of current AI. Deep learning and neurosymbolic AI lack a general set of conditions to ensure that desirable properties are satisfied. Instead, there is a plethora of encoding and knowledge extraction approaches designed for particular cases. To rectify this, we introduced a framework for semantic encoding, making explicit the mapping between neural networks and logic, and characterizing the common ingredients of the various existing approaches. In this paper, we describe succinctly and exemplify how logical semantics and neural networks are linked through this framework, we review some of the most prominent approaches and techniques developed for neural encoding and knowledge extraction, provide a formal definition of our framework, and discuss some of the difficulties of identifying a semantic encoding in practice in light of analogous problems in the philosophy of mind.

Related papers

• Foundations of Artificial Intelligence Frameworks: Notion and Limits of AGI [0.0]
  We argue that artificial general intelligence cannot emerge from current neural network paradigms regardless of scale.<n>We propose a framework distinguishing existential facilities (computational substrate) from architectural organization.
  arXiv  Detail & Related papers  (2025-11-23T16:18:13Z)
• Reasoning in Neurosymbolic AI [2.25467522343563]
  principled integration of reasoning and learning in neural networks is a main objective of the area of neurosymbolic Artificial Intelligence.<n>A simple energy-based neurosymbolic AI system is described that can represent and reason formally about any propositional logic formula.
  arXiv  Detail & Related papers  (2025-05-22T11:57:04Z)
• A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectives [2.5782420501870296]
  Symbolic AI excels in reasoning, explainability, and knowledge representation but faces challenges in processing complex real-world data with noise.<n>Deep learning (Black-Box systems) research breakthroughs in neural networks are notable, yet they lack reasoning and interpretability.<n>Neuro-symbolic AI (NeSy) attempts to bridge this gap by integrating logical reasoning into neural networks, enabling them to learn and reason with symbolic representations.
  arXiv  Detail & Related papers  (2025-03-23T21:33:38Z)
• Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents [55.63497537202751]
  Article explores the convergence of connectionist and symbolic artificial intelligence (AI) Traditionally, connectionist AI focuses on neural networks, while symbolic AI emphasizes symbolic representation and logic. Recent advancements in large language models (LLMs) highlight the potential of connectionist architectures in handling human language as a form of symbols.
  arXiv  Detail & Related papers  (2024-07-11T14:00:53Z)
• A Review of Neuroscience-Inspired Machine Learning [58.72729525961739]
  Bio-plausible credit assignment is compatible with practically any learning condition and is energy-efficient. In this paper, we survey several vital algorithms that model bio-plausible rules of credit assignment in artificial neural networks. We conclude by discussing the future challenges that will need to be addressed in order to make such algorithms more useful in practical applications.
  arXiv  Detail & Related papers  (2024-02-16T18:05:09Z)
• Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignment [65.268245109828]
  We examine algorithms for conducting credit assignment in artificial neural networks that are inspired or motivated by neurobiology. We organize the ever-growing set of brain-inspired learning schemes into six general families and consider these in the context of backpropagation of errors. The results of this review are meant to encourage future developments in neuro-mimetic systems and their constituent learning processes.
  arXiv  Detail & Related papers  (2023-12-01T05:20:57Z)
• A Neuro-mimetic Realization of the Common Model of Cognition via Hebbian Learning and Free Energy Minimization [55.11642177631929]
  Large neural generative models are capable of synthesizing semantically rich passages of text or producing complex images. We discuss the COGnitive Neural GENerative system, such an architecture that casts the Common Model of Cognition.
  arXiv  Detail & Related papers  (2023-10-14T23:28:48Z)
• Extensions to Generalized Annotated Logic and an Equivalent Neural Architecture [4.855957436171202]
  We propose a list of desirable criteria for neuro symbolic systems and examine how some of the existing approaches address these criteria. We then propose an extension to annotated generalized logic that allows for the creation of an equivalent neural architecture. Unlike previous approaches that rely on continuous optimization for the training process, our framework is designed as a binarized neural network that uses discrete optimization.
  arXiv  Detail & Related papers  (2023-02-23T17:39:46Z)
• A Semantic Framework for Neuro-Symbolic Computing [0.36832029288386137]
  The field of neuro-symbolic AI aims to benefit from the combination of neural networks and symbolic systems.<n>No common definition of encoding exists that can enable a precise, theoretical comparison of neuro-symbolic methods.<n>This paper addresses this problem by introducing a semantic framework for neuro-symbolic AI.
  arXiv  Detail & Related papers  (2022-12-22T22:00:58Z)
• Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing [73.0977635031713]
  Neural-symbolic computing (NeSy) has been an active research area of Artificial Intelligence (AI) for many years. NeSy shows promise of reconciling the advantages of reasoning and interpretability of symbolic representation and robust learning in neural networks.
  arXiv  Detail & Related papers  (2022-10-28T04:38:10Z)
• Neuro-Symbolic Learning of Answer Set Programs from Raw Data [54.56905063752427]
  Neuro-Symbolic AI aims to combine interpretability of symbolic techniques with the ability of deep learning to learn from raw data. We introduce Neuro-Symbolic Inductive Learner (NSIL), an approach that trains a general neural network to extract latent concepts from raw data. NSIL learns expressive knowledge, solves computationally complex problems, and achieves state-of-the-art performance in terms of accuracy and data efficiency.
  arXiv  Detail & Related papers  (2022-05-25T12:41:59Z)
• Neuro-symbolic Architectures for Context Understanding [59.899606495602406]
  We propose the use of hybrid AI methodology as a framework for combining the strengths of data-driven and knowledge-driven approaches. Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks.
  arXiv  Detail & Related papers  (2020-03-09T15:04:07Z)

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.