Neuromyotonic Fusion: Integrating Symbolic Reasoning with Deep Learning Architectures

Abstract

Because computational context comprehension refers to an agent’s capacity to combine different knowledge sources for decision-making, it is typically recognized as a

necessary precondition for advanced machine reasoning skills, such those found in artificial intelligence (AI). Two traditional approaches in the search for such machine sense-making capabilities are data-driven and knowledge-driven methodologies.

While data-driven approaches aim to simulate the statistical regularities of occurrences through real-world observations, they lack mechanisms for organically adding outside information and are nonetheless challenging to comprehend. Conversely, knowledge-driven methods, combine structured knowledge bases, perform symbolic reasoning based on axiomatic principles, and are more interpretable in their inferential processing; however, they often lack the ability to estimate the statistical salience of an inference. To combat these issues, we propose the use of hybrid AI methodology as a general framework for combining the strengths of both 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. We further ground our discussion in two applications of neuro-symbolism and, in both cases, show that our systems maintain interpretability while achieving comparable performance, relative to the state-of-the-art.

DOI - https://doi.org/10.65525/SVUP.9788199778009.2026.44-52