Neuro-Symbolic

Neuro-Symbolic approaches aim to bridge the gap between the continuous domain of connections models (such as deep neural networks) and discrete models and algorithms used in symbolic reasoning, which includes logical and probabilistic reasoning, optimization, search, and planning, among others.

papers/Improving Out-of-Distribution Detection with Markov Logic Networks (06 Jun. 2025)
Our paper Improving Out-of-Distribution Detection with Markov Logic Network has been accepted at the ICML. In it, we propose a probabilistic extension of Out-of-Distribution Detection with Logical Reasoning, as well as a simple algorithm to mine logical constraints for OOD detection from a dataset. Abstract § Out-of-distribution (OOD) detection is essential for ensuring the reliability of deep learning models operating in open-world scenarios. Current OOD detectors mainly rely on statistical …
Categories: Neuro-Symbolic
174 Words, Tagged with: ICML · Neuro-Symbolic · Anomaly Detection
Thumbnail for Improving Out-of-Distribution Detection with Markov Logic Networks
papers/Language Models as Reasoners for Out-of-Distribution Detection (17 Sep. 2024)
Our paper, Language Models as Reasoners for Out-of-Distribution Detection, was presented at the Workshop on AI Safety Engineering (WAISE) 2024 and received the best paper award by popular vote. It constitutes an extension of our idea of Out-of-Distribution Detection with Logical Reasoning, where we replaced the prolog-based reasoning component with an LLM. Abstract § Deep neural networks (DNNs) are prone to making wrong predictions with high confidence for data that does not stem from their …
Categories: Anomaly Detection · Neuro-Symbolic
195 Words, Tagged with: SafeComp · Anomaly Detection · Large Language Models · Neuro-Symbolic
Thumbnail for Language Models as Reasoners for Out-of-Distribution Detection
papers/Out-of-Distribution Detection with Logical Reasoning (04 Jan. 2024)
Our paper Out-of-Distribution Detction with Logical Reasoning has been accepted on the WACV 2024. Abstract § Machine Learning models often only generalize reliably to samples from the training distribution. Consequentially, detecting when input data is out-of-distribution (OOD) is crucial, especially in safety-critical applications. Current OOD detection methods, however, tend to be domain agnostic and often fail to incorporate valuable prior knowledge about the structure of the training …
Categories: Anomaly Detection · Neuro-Symbolic
226 Words, Tagged with: WACV · Anomaly Detection · Neuro-Symbolic
Thumbnail for Out-of-Distribution Detection with Logical Reasoning
papers/Towards Deep Anomaly Detection with Structured Knowledge Representations (15 Jun. 2023)
My paper Towards Deep Anomaly Detection with Structured Knowledge Representations has been accepted on the Workshop on AI Safety Engineering at SafeComp. Abstract § Machine learning models tend to only make reliable predictions for inputs that are similar to the training data. Consequentially, anomaly detection, which can be used to detect unusual inputs, is critical for ensuring the safety of machine learning agents operating in open environments. In this work, we identify and discuss several …
Categories: Anomaly Detection · Neuro-Symbolic
181 Words, Tagged with: SafeComp · Anomaly Detection · Neuro-Symbolic
Thumbnail for Towards Deep Anomaly Detection with Structured Knowledge Representations