Tillman Weyde
YOU?
Author Swipe
View article: Evaluating LLMs for Combinatorial Optimization: One-Phase and Two-Phase Heuristics for 2D Bin-Packing
Evaluating LLMs for Combinatorial Optimization: One-Phase and Two-Phase Heuristics for 2D Bin-Packing Open
This paper presents an evaluation framework for assessing Large Language Models' (LLMs) capabilities in combinatorial optimization, specifically addressing the 2D bin-packing problem. We introduce a systematic methodology that combines LLM…
View article: NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection
NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection Open
NeSy4VRD NeSy4VRD is a multifaceted, multipurpose resource designed to foster neurosymbolic AI (NeSy) research, particularly NeSy research using Semantic Web technologies such as OWL ontologies, OWL-based knowledge graphs and OWL-based rea…
View article: Disentangling concept semantics via multilingual averaging in Sparse Autoencoders
Disentangling concept semantics via multilingual averaging in Sparse Autoencoders Open
Connecting LLMs with formal knowledge representation and reasoning is a promising approach to address their shortcomings. Embeddings and sparse autoencoders are widely used to represent textual content, but the semantics are entangled with…
View article: Wavelet-Filtering of Symbolic Music Representations for Folk Tune Segmentation and Classification
Wavelet-Filtering of Symbolic Music Representations for Folk Tune Segmentation and Classification Open
The aim of this study is to evaluate a machine-learning method in which symbolic representations of folk songs are segmented and classified into tune families with Haar-wavelet filtering. The method is compared with previously proposed Ges…
View article: Prediction of Snacking Behavior Involving Snacks Having High Levels of Saturated Fats, Salt, or Sugar Using Only Information on Previous Instances of Snacking: Survey- and App-Based Study
Prediction of Snacking Behavior Involving Snacks Having High Levels of Saturated Fats, Salt, or Sugar Using Only Information on Previous Instances of Snacking: Survey- and App-Based Study Open
Background Consuming high amounts of foods or beverages with high levels of saturated fats, salt, or sugar (HFSS) can be harmful for health. Many snacks fall into this category (HFSS snacks). However, the palatability of these snacks means…
View article: Explorations of the Softmax Space: Knowing When the Neural Network Doesn't Know
Explorations of the Softmax Space: Knowing When the Neural Network Doesn't Know Open
Ensuring the reliability of automated decision-making based on neural networks will be crucial as Artificial Intelligence systems are deployed more widely in critical situations. This paper proposes a new approach for measuring confidence …
View article: Denoising Diffusion Probabilistic Model for Realistic Financial Correlation Matrices
Denoising Diffusion Probabilistic Model for Realistic Financial Correlation Matrices Open
Financial correlation matrices play a vital role in various quantitative finance applications, but generating synthetic correlation matrices that accurately reflect market structures and stylized facts remains challenging. We introduce a n…
View article: OWL2Vec4OA: Tailoring Knowledge Graph Embeddings for Ontology Alignment
OWL2Vec4OA: Tailoring Knowledge Graph Embeddings for Ontology Alignment Open
Ontology alignment is integral to achieving semantic interoperability as the number of available ontologies covering intersecting domains is increasing. This paper proposes OWL2Vec4OA, an extension of the ontology embedding system OWL2Vec*…
View article: When to Accept Automated Predictions and When to Defer to Human Judgment?
When to Accept Automated Predictions and When to Defer to Human Judgment? Open
Ensuring the reliability and safety of automated decision-making is crucial. It is well-known that data distribution shifts in machine learning can produce unreliable outcomes. This paper proposes a new approach for measuring the reliabili…
View article: The Misclassification Likelihood Matrix: Some Classes Are More Likely To Be Misclassified Than Others
The Misclassification Likelihood Matrix: Some Classes Are More Likely To Be Misclassified Than Others Open
This study introduces the Misclassification Likelihood Matrix (MLM) as a novel tool for quantifying the reliability of neural network predictions under distribution shifts. The MLM is obtained by leveraging softmax outputs and clustering t…
View article: JazzDAP: Collaborative Research Tools for Digital Jazz Archives
JazzDAP: Collaborative Research Tools for Digital Jazz Archives Open
This paper introduces a novel web platform designed for exploration, analysis, and collaboration in the jazz music domain called JazzDAP. Our platform integrates advanced music information retrieval techniques with user-friendly interfaces…
View article: Derivative-based regularization for regression
Derivative-based regularization for regression Open
In this work, we introduce a novel approach to regularization in multivariable regression problems. Our regularizer, called DLoss, penalises differences between the model's derivatives and derivatives of the data generating function as est…
View article: Prediction of Snacking Behavior Involving Snacks Having High Levels of Saturated Fats, Salt, or Sugar Using Only Information on Previous Instances of Snacking: Survey- and App-Based Study (Preprint)
Prediction of Snacking Behavior Involving Snacks Having High Levels of Saturated Fats, Salt, or Sugar Using Only Information on Previous Instances of Snacking: Survey- and App-Based Study (Preprint) Open
BACKGROUND Consuming high amounts of foods or beverages with high levels of saturated fats, salt, or sugar (HFSS) can be harmful for health. Many snacks fall into this category (HFSS snacks). However, the palatability of these snacks mean…
View article: Development of an explainable artificial intelligence model for Asian vascular wound images
Development of an explainable artificial intelligence model for Asian vascular wound images Open
Chronic wounds contribute to significant healthcare and economic burden worldwide. Wound assessment remains challenging given its complex and dynamic nature. The use of artificial intelligence (AI) and machine learning methods in wound ana…
View article: Improved Data Generation for Enhanced Asset Allocation: A Synthetic Dataset Approach for the Fixed Income Universe
Improved Data Generation for Enhanced Asset Allocation: A Synthetic Dataset Approach for the Fixed Income Universe Open
We present a novel process for generating synthetic datasets tailored to assess asset allocation methods and construct portfolios within the fixed income universe. Our approach begins by enhancing the CorrGAN model to generate synthetic co…
View article: NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection
NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection Open
NeSy4VRD is a multifaceted resource designed to support the development of neurosymbolic AI (NeSy) research. NeSy4VRD re-establishes public access to the images of the VRD dataset and couples them with an extensively revised, quality-impro…
View article: NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection
NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection Open
NeSy4VRD NeSy4VRD is a multifaceted, multipurpose resource designed to foster neurosymbolic AI (NeSy) research, particularly NeSy research using Semantic Web technologies such as OWL ontologies, OWL-based knowledge graphs and OWL-based rea…
View article: NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection
NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection Open
NeSy4VRD NeSy4VRD is a multifaceted, multipurpose resource designed to foster neurosymbolic AI (NeSy) research, particularly NeSy research using Semantic Web technologies such as OWL ontologies, OWL-based knowledge graphs and OWL-based rea…
View article: NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection
NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection Open
The NeSy4VRD dataset consists of an image dataset and matching visual relationship annotations. The images of the dataset are same as those that were once publicly available as part of the VRD dataset. The visual relationship annotations a…
View article: Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks
Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks Open
Previous work has established that RNNs with an unbounded activation function have the capacity to count exactly. However, it has also been shown that RNNs are challenging to train effectively and generally do not learn exact counting beha…
View article: Towards a Unified Model for Generating Answers and Explanations in Visual Question Answering
Towards a Unified Model for Generating Answers and Explanations in Visual Question Answering Open
The field of visual question answering (VQA) has recently seen a surge in research focused on providing explanations for predicted answers. However, current systems mostly rely on separate models to predict answers and generate explanation…
View article: Learning Speech Emotion Representations in the Quaternion Domain
Learning Speech Emotion Representations in the Quaternion Domain Open
The modeling of human emotion expression in speech signals is an important, yet challenging task. The high resource demand of speech emotion recognition models, combined with the general scarcity of emotion-labelled data are obstacles to t…
View article: Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks
Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks Open
Previous work has established that RNNs with an unbounded activation function have the capacity to count exactly. However, it has also been shown that RNNs are challenging to train effectively and generally do not learn exact counting beha…
View article: Towards a Unified Model for Generating Answers and Explanations in Visual Question Answering
Towards a Unified Model for Generating Answers and Explanations in Visual Question Answering Open
The field of visual question answering (VQA) has recently seen a surge in research focused on providing explanations for predicted answers. However, current systems mostly rely on separate models to predict answers and generate explanation…
View article: Exploring the Long-Term Generalization of Counting Behavior in RNNs
Exploring the Long-Term Generalization of Counting Behavior in RNNs Open
In this study, we investigate the generalization of LSTM, ReLU and GRU models on counting tasks over long sequences. Previous theoretical work has established that RNNs with ReLU activation and LSTMs have the capacity for counting with sui…
View article: The Jazz Ontology: A semantic model and large-scale RDF repositories for jazz
The Jazz Ontology: A semantic model and large-scale RDF repositories for jazz Open
International audience
View article: Evaluation of Fake News Detection with Knowledge-Enhanced Language Models
Evaluation of Fake News Detection with Knowledge-Enhanced Language Models Open
Recent advances in fake news detection have exploited the success of large-scale pre-trained language models (PLMs). The predominant state-of-the-art approaches are based on fine-tuning PLMs on labelled fake news datasets. However, large-s…