Search Results for author: Pascal Hitzler

Found 30 papers, 4 papers with code

Error-margin Analysis for Hidden Neuron Activation Labels

no code implementations14 May 2024 Abhilekha Dalal, Rushrukh Rayan, Pascal Hitzler

Understanding how high-level concepts are represented within artificial neural networks is a fundamental challenge in the field of artificial intelligence.

Information Retrieval Retrieval

On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysis

no code implementations21 Apr 2024 Abhilekha Dalal, Rushrukh Rayan, Adrita Barua, Eugene Y. Vasserman, Md Kamruzzaman Sarker, Pascal Hitzler

A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons: accurate interpretations would help answer the question of what a deep learning system internally detects as relevant in the input, demystifying the otherwise black-box nature of deep learning systems.

Explanation Generation

Concept Induction using LLMs: a user experiment for assessment

no code implementations18 Apr 2024 Adrita Barua, Cara Widmer, Pascal Hitzler

To evaluate the output, we compare the concepts generated by the LLM with two other methods: concepts generated by humans and the ECII heuristic concept induction system.

Common Sense Reasoning Explainable artificial intelligence +4

Towards Complex Ontology Alignment using Large Language Models

no code implementations16 Apr 2024 Reihaneh Amini, Sanaz Saki Norouzi, Pascal Hitzler, Reza Amini

Ontology alignment, a critical process in the Semantic Web for detecting relationships between different ontologies, has traditionally focused on identifying so-called "simple" 1-to-1 relationships through class labels and properties comparison.

Commonsense Ontology Micropatterns

no code implementations28 Feb 2024 Andrew Eells, Brandon Dave, Pascal Hitzler, Cogan Shimizu

The previously introduced Modular Ontology Modeling methodology (MOMo) attempts to mimic the human analogical process by using modular patterns to assemble more complex concepts.

Common Sense Reasoning

Conversational Ontology Alignment with ChatGPT

no code implementations18 Aug 2023 Sanaz Saki Norouzi, Mohammad Saeid Mahdavinejad, Pascal Hitzler

This study evaluates the applicability and efficiency of ChatGPT for ontology alignment using a naive approach.

Language Modelling Large Language Model +1

Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive Reasoning

1 code implementation8 Aug 2023 Abhilekha Dalal, Md Kamruzzaman Sarker, Adrita Barua, Eugene Vasserman, Pascal Hitzler

A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons: accurate interpretations would provide insights into the question of what a deep learning system has internally detected as relevant on the input, demystifying the otherwise black-box character of deep learning systems.

A Modular Ontology for MODS -- Metadata Object Description Schema

no code implementations31 Jul 2023 Rushrukh Rayan, Cogan Shimizu, Heidi Sieverding, Pascal Hitzler

The Metadata Object Description Schema (MODS) was developed to describe bibliographic concepts and metadata and is maintained by the Library of Congress.

Knowledge Graphs Object

An Ontology Design Pattern for Role-Dependent Names

no code implementations3 May 2023 Rushrukh Rayan, Cogan Shimizu, Pascal Hitzler

We present an ontology design pattern for modeling Names as part of Roles, to capture scenarios where an Agent performs different Roles using different Names associated with the different Roles.

Explaining Deep Learning Hidden Neuron Activations using Concept Induction

no code implementations23 Jan 2023 Abhilekha Dalal, Md Kamruzzaman Sarker, Adrita Barua, Pascal Hitzler

One of the current key challenges in Explainable AI is in correctly interpreting activations of hidden neurons.

Towards Human-Compatible XAI: Explaining Data Differentials with Concept Induction over Background Knowledge

no code implementations27 Sep 2022 Cara Widmer, Md Kamruzzaman Sarker, Srikanth Nadella, Joshua Fiechter, Ion Juvina, Brandon Minnery, Pascal Hitzler, Joshua Schwartz, Michael Raymer

Concept induction, which is based on formal logical reasoning over description logics, has been used in ontology engineering in order to create ontology (TBox) axioms from the base data (ABox) graph.

Explainable Artificial Intelligence (XAI) Logical Reasoning

On the Capabilities of Pointer Networks for Deep Deductive Reasoning

no code implementations17 Jun 2021 Monireh Ebrahimi, Aaron Eberhart, Pascal Hitzler

The importance of building neural networks that can learn to reason has been well recognized in the neuro-symbolic community.

Decoder Knowledge Graphs

Neuro-Symbolic Artificial Intelligence: Current Trends

no code implementations11 May 2021 Md Kamruzzaman Sarker, Lu Zhou, Aaron Eberhart, Pascal Hitzler

Neuro-Symbolic Artificial Intelligence -- the combination of symbolic methods with methods that are based on artificial neural networks -- has a long-standing history.

Neural Fuzzy Extractors: A Secure Way to Use Artificial Neural Networks for Biometric User Authentication

no code implementations18 Mar 2020 Abhishek Jana, Md. Kamruzzaman Sarker, Monireh Ebrahimi, Pascal Hitzler, George T. Amariucai

Powered by new advances in sensor development and artificial intelligence, the decreasing cost of computation, and the pervasiveness of handheld computation devices, biometric user authentication (and identification) is rapidly becoming ubiquitous.

Completion Reasoning Emulation for the Description Logic EL+

1 code implementation11 Dec 2019 Aaron Eberhart, Monireh Ebrahimi, Lu Zhou, Cogan Shimizu, Pascal Hitzler

We present a new approach to integrating deep learning with knowledge-based systems that we believe shows promise.

MODL: A Modular Ontology Design Library

no code implementations10 Apr 2019 Cogan Shimizu, Quinn Hirt, Pascal Hitzler

Pattern-based, modular ontologies have several beneficial properties that lend themselves to FAIR data practices, especially as it pertains to Interoperability and Reusability.

Efficient Concept Induction for Description Logics

1 code implementation8 Dec 2018 Md. Kamruzzaman Sarker, Pascal Hitzler

Concept Induction refers to the problem of creating complex Description Logic class descriptions (i. e., TBox axioms) from instance examples (i. e., ABox data).

Reasoning over RDF Knowledge Bases using Deep Learning

2 code implementations9 Nov 2018 Monireh Ebrahimi, Md. Kamruzzaman Sarker, Federico Bianchi, Ning Xie, Derek Doran, Pascal Hitzler

Semantic Web knowledge representation standards, and in particular RDF and OWL, often come endowed with a formal semantics which is considered to be of fundamental importance for the field.

Knowledge Graphs

Rule-based OWL Modeling with ROWLTab Protege Plugin

no code implementations30 Aug 2018 Md. Kamruzzaman Sarker, Adila Krisnadhi, David Carral, Pascal Hitzler

It has been argued that it is much easier to convey logical statements using rules rather than OWL (or description logic (DL)) axioms.

Modeling OWL with Rules: The ROWL Protege Plugin

no code implementations30 Aug 2018 Md. Kamruzzaman Sarker, David Carral, Adila A. Krisnadhi, Pascal Hitzler

In our experience, some ontology users find it much easier to convey logical statements using rules rather than OWL (or description logic) axioms.

OWLAx: A Protege Plugin to Support Ontology Axiomatization through Diagramming

no code implementations30 Aug 2018 Md. Kamruzzaman Sarker, Adila A. Krisnadhi, Pascal Hitzler

Once the conceptual overview, in terms of a somewhat informal class diagram, has been designed in the course of engineering an ontology, the process of adding many of the appropriate logical axioms is mostly a routine task.

A Tutorial on Modular Ontology Modeling with Ontology Design Patterns: The Cooking Recipes Ontology

no code implementations25 Aug 2018 Pascal Hitzler, Adila Krisnadhi

We provide a detailed example for modular ontology modeling based on ontology design patterns.

A Practical Acyclicity Notion for Query Answering over Horn-SRIQ Ontologies

no code implementations19 Apr 2018 David Carral, Cristina Feier, Pascal Hitzler

Conjunctive query answering over expressive Horn Description Logic ontologies is a relevant and challenging problem which, in some cases, can be addressed by application of the chase algorithm.

Relating Input Concepts to Convolutional Neural Network Decisions

no code implementations21 Nov 2017 Ning Xie, Md. Kamruzzaman Sarker, Derek Doran, Pascal Hitzler, Michael Raymer

Many current methods to interpret convolutional neural networks (CNNs) use visualization techniques and words to highlight concepts of the input seemingly relevant to a CNN's decision.

Decision Making Scene Recognition

Neural-Symbolic Learning and Reasoning: A Survey and Interpretation

no code implementations10 Nov 2017 Tarek R. Besold, Artur d'Avila Garcez, Sebastian Bader, Howard Bowman, Pedro Domingos, Pascal Hitzler, Kai-Uwe Kuehnberger, Luis C. Lamb, Daniel Lowd, Priscila Machado Vieira Lima, Leo de Penning, Gadi Pinkas, Hoifung Poon, Gerson Zaverucha

Recent studies in cognitive science, artificial intelligence, and psychology have produced a number of cognitive models of reasoning, learning, and language that are underpinned by computation.

Philosophy

On the Ontological Modeling of Trees

no code implementations13 Oct 2017 David Carral, Pascal Hitzler, Hilmar Lapp, Sebastian Rudolph

Trees -- i. e., the type of data structure known under this name -- are central to many aspects of knowledge organization.

Explaining Trained Neural Networks with Semantic Web Technologies: First Steps

no code implementations11 Oct 2017 Md. Kamruzzaman Sarker, Ning Xie, Derek Doran, Michael Raymer, Pascal Hitzler

The ever increasing prevalence of publicly available structured data on the World Wide Web enables new applications in a variety of domains.

Dimensions of Neural-symbolic Integration - A Structured Survey

no code implementations10 Nov 2005 Sebastian Bader, Pascal Hitzler

Research on integrated neural-symbolic systems has made significant progress in the recent past.

Cannot find the paper you are looking for? You can Submit a new open access paper.