KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning

Adaptive Neuro-Fuzzy Inference System (ANFIS) was designed to combine the learning capabilities of neural network with the reasoning transparency of fuzzy logic. However, conventional ANFIS architectures suffer from structural complexity, where the product-based inference mechanism causes an exponential explosion of rules in high-dimensional spaces. We herein propose the \textbf{K}olmogorov-\textbf{A}rnold Neuro-Fuzzy Inference System (KANFIS), a compact neuro-symbolic architecture that unifies fuzzy reasoning with additive function decomposition. KANFIS employs an additive aggregation mechanism, under which both model parameters and rule complexity scale linearly with input dimensionality rather than exponentially. Furthermore, KANFIS is compatible with both Type-1 (T1) and Interval Type-2 (IT2) fuzzy logic systems, enabling explicit modeling of uncertainty and ambiguity in fuzzy representations. By using sparse masking mechanisms, KANFIS generates compact and structured rule sets, resulting in an intrinsically interpretable model with clear rule semantics and transparent inference processes. Empirical results demonstrate that KANFIS achieves competitive performance against representative neural and neuro-fuzzy baselines.

Modern interpretable AI models often struggle with high-dimensional data because their rule structures become increasingly complex as the number of input features grows. In this work, we propose KANFIS, a neuro-symbolic framework that combines fuzzy logic with additive neural representations. KANFIS alleviates the high-dimensional problem by avoiding the exponential growth of fuzzy rules, giving the model better scalability and computational efficiency on large datasets. At the same time, it can generate concise and human-readable “IF-THEN” rules, making the prediction process easier to understand. Experimental results on multiple medical, industrial, and scientific datasets show that KANFIS achieves competitive predictive accuracy while maintaining clear and meaningful rule structures. Overall, KANFIS provides an effective framework for building scalable and interpretable AI systems.