Neurosymbolic Learning

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, up 67% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 37

All topics

Learning to Reason: Targeted Knowledge Discovery and Fuzzy Logic Update for Robust Image Recognition
Apr 30, 2026Gurucharan Srinivas, Joshua Niemeijer, Frank KösterNeurosymbolic Learning Image Classification
German Aerospace Center (DLR)
Constraint-Based Analysis of Reasoning Shortcuts in Neurosymbolic Learning
Apr 25, 2026Akihiro Takemura, Katsumi Inoue, Masaaki NishinoSymbolic Reasoning Constraint Satisfaction
National Institute of Informatics, Tokyo, Japan · Communication Science Laboratories, NTT, Inc., Japan
Neuro-Symbolic ODE Discovery with Latent Grammar Flow
Apr 17, 2026Karin Yu, Eleni Chatzi, Georgios KissasAutonomous Scientific Discovery Neurosymbolic Learning
Institute of Structural Engineering, ETH Zurich, Zurich, Switzerland · ETH AI Center, ETH Zurich, Zurich, Switzerland · Swiss Data Science Center, Zurich, Switzerland
From Local Corrections to Generalized Skills: Improving Neuro-Symbolic Policies with MEMO
Mar 4, 2026Benjamin A. Christie, Yinlong Dai, Mohammad Bararjanianbahnamiri +2Robot Skill Learning Language-Conditioned Robot Manipulation
Collab, Dept. of Mechanical Engineering, Virginia Tech, Blacksburg, USA. · TEA Lab, Dept. of Mechanical Engineering, Virginia Tech, Blacksburg, USA.
KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning
Feb 3, 2026Binbin Yong, Haoran Pei, Jun Shen +3Interpretable ML Fuzzy Logic
School of Information Science and Engineering, Lanzhou University, China · School of Computing and Information Technology, University of Wollongong, Australia · Department of Data Science and Artificial Intelligence, Monash University, Australia
Neural Logic Networks for Interpretable Classification
Aug 11, 2025Vincent Perreault, Katsumi Inoue, Richard Labib +1Boolean Function Learning Neural Network Interpretability
Department of Mathematics and Industrial Engineering Polytechnique Montréal · National Institute of Informatics, Tokyo
NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models
Date pendingZiyue Zhu, Shangyang Wu, Shuai Zhao +8Vision-Language-Action Models Robotic Manipulation
Beijing University of Posts and Telecommunications · Nanyang Technological University

Apr 30, 2026, cs.CVJ/K move · Enter open · S save

Learning to Reason: Targeted Knowledge Discovery and Fuzzy Logic Update for Robust Image Recognition

Gurucharan Srinivas, Joshua Niemeijer, Frank Köster

German Aerospace Center (DLR)

Neurosymbolic Learning Image Classification

Open paper AskPDF arXiv

Integrating domain knowledge into deep neural networks is a promising way to improve generalization. Existing methods either encode prior knowledge in the loss function or apply post-processing modules, but both depend on identifying useful symbolic knowledge to integrate. Since such rules are often unavailable in real-world vision tasks, we propose a method for targeted knowledge discovery. We propose a Differentiable Knowledge Unit (DKU) that enables modulating the classifier logits, yielding refined class probabilities. The DKU uses implication rules to represent relationships between task classes and implicit concepts learned entirely from the main task supervision, without requiring concept labels. Concepts are identified by dedicated classifiers, whose probabilities are passed to DKU alongside the primary class probabilities. DKU computes a logic-based adjustment vector via fuzzy inference, which modulates the primary class logits to yield refined class probabilities. When concept classifiers represent concepts that do not support the logical rule structure, the resulting adjustments to the class probabilities do not directly minimize the supervision loss. Consequently, optimizing the supervision loss on these adjusted class probabilities implicitly trains the concept classifiers. We construct the rule base so that bidirectional logical relations connect concepts and classes. We enforce the concepts to be distinct from each other and with respect to the classes. This design enforces a clean supervision signal for concept learning. We evaluate our methods on the PASCAL-VOC, COCO, and MedMNIST datasets. We demonstrate improvement through our knowledge integration across these datasets. We conduct domain generalization and hard-sample ablation studies and find that our implicit knowledge discovery and integration outperforms the baseline.

Momentum

Related topics

Latest papers 37