TY - GEN
T1 - Neuromorphic Knowledge Representation
T2 - 21st International Conference on Intelligent Tutoring Systems, ITS 2025
AU - Jhajj, Gaganpreet
AU - Gustafson, Jerry Ryan David
AU - Morland, Raymond
AU - Gutierrez, Carlos Enrique
AU - Lin, Michael Pin Chuan
AU - Dewan, M. Ali Akber
AU - Lin, Fuhua
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026
Y1 - 2026
N2 - This paper explores a neuromorphic approach to semantic knowledge representation using spiking neural networks (SNNs) for relational inference within knowledge graphs (KGs). While traditional KG models often rely on dense embeddings that lack interpretability, SNNs offer a biologically inspired alternative by encoding relationships through discrete, event-driven spikes. We evaluate three architectures—LIF-Base, RecurrentSNN, and LiquidSNN—on a dataset of 54 computer science-related KG triplets. Performance is assessed using relationship classification accuracy, temporal and spatial stability, and spike variability. Results show that relationship types produce distinct spike activation patterns, with LiquidSNN achieving the highest accuracy and spatial coherence. These findings support the potential of SNNs for structured, interpretable KG reasoning, with future applications in adaptive learning systems and explainable AI.
AB - This paper explores a neuromorphic approach to semantic knowledge representation using spiking neural networks (SNNs) for relational inference within knowledge graphs (KGs). While traditional KG models often rely on dense embeddings that lack interpretability, SNNs offer a biologically inspired alternative by encoding relationships through discrete, event-driven spikes. We evaluate three architectures—LIF-Base, RecurrentSNN, and LiquidSNN—on a dataset of 54 computer science-related KG triplets. Performance is assessed using relationship classification accuracy, temporal and spatial stability, and spike variability. Results show that relationship types produce distinct spike activation patterns, with LiquidSNN achieving the highest accuracy and spatial coherence. These findings support the potential of SNNs for structured, interpretable KG reasoning, with future applications in adaptive learning systems and explainable AI.
KW - Explainability and Interpretability
KW - Knowledge Graphs (KGs)
KW - Neuromorphic Computing
KW - Spiking Neural Networks (SNNs)
UR - https://www.scopus.com/pages/publications/105013047693
U2 - 10.1007/978-3-031-98284-2_13
DO - 10.1007/978-3-031-98284-2_13
M3 - Published Conference contribution
AN - SCOPUS:105013047693
SN - 9783031982835
T3 - Lecture Notes in Computer Science
SP - 159
EP - 165
BT - Generative Systems and Intelligent Tutoring Systems - 21st International Conference, ITS 2025, Proceedings
A2 - Graf, Sabine
A2 - Markos, Angelos
Y2 - 2 June 2025 through 6 June 2025
ER -