Tillman Weyde | City, University of London (original) (raw)

Tillman Weyde

Researcher in Machine Learning and its application to Audio, Language and Music.

less

Uploads

Papers by Tillman Weyde

Research paper thumbnail of Understandability of Global Post-hoc Explanations of Black-box Models: Dataset and Analysis

The dataset contains the data collected in a user study carried out to evaluate the impact of usi... more The dataset contains the data collected in a user study carried out to evaluate the impact of using domain knowledge, ontologies, in the creation of global post-hoc explanations of black-box models. The research hypothesis was that the use of ontologies could enhance the understandability of explanations by humans. To validate this research hypothesis we ran a user study where participants were asked to carry out several tasks. In each task, the answers, time of response, and user understandability and confidence were collected and measured. The data analysis revealed that the use of ontologies do enhance the understandability of explanations of black-box models by human users, in particular, in the form of decision trees explaining artificial neural networks.

Research paper thumbnail of Multiple Viewpiont Melodic Prediction with Fixed-Context Neural Networks

International Symposium/Conference on Music Information Retrieval, 2014

Research paper thumbnail of Perceiving and predicting expressive rhythm with recurrent neural networks

Research paper thumbnail of Melodic structure and automatic classification in Bach's 2-part inventions

Research paper thumbnail of Hybrid Long- and Short-Term Models of Folk Melodies

International Symposium/Conference on Music Information Retrieval, 2015

Research paper thumbnail of Opuscope - Towards a Corpus-Based Music Repository

International Symposium/Conference on Music Information Retrieval, 2002

Research paper thumbnail of Studying the Effect of Metre Perception on Rhythm and Melody Modelling with LSTMs

Zenodo (CERN European Organization for Nuclear Research), Oct 4, 2014

Research paper thumbnail of The Influence of Pitch on Melodic Segmentation

International Symposium/Conference on Music Information Retrieval, 2004

Research paper thumbnail of A Wavelet-Based Approach to Pattern Discovery in Melodies

Springer eBooks, Oct 28, 2015

Research paper thumbnail of Concepts of the MUSITECH infrastructure for Internet-based interactive musical applications

Research paper thumbnail of Efficient Melody Retrieval with Motif Contour Classes

International Symposium/Conference on Music Information Retrieval, 2005

Research paper thumbnail of NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection

arXiv (Cornell University), May 22, 2023

Research paper thumbnail of Integrating Convexity and Compactness into the ISSM: Melodic Analysis of Music

Research paper thumbnail of Learned complex masks for multi-instrument source separation

arXiv (Cornell University), Mar 23, 2021

Research paper thumbnail of Anti-Transfer Learning for Task Invariance in Convolutional Neural Networks for Speech Processing

arXiv (Cornell University), Jun 11, 2020

Research paper thumbnail of Learning Speech Emotion Representations in the Quaternion Domain

arXiv (Cornell University), Apr 5, 2022

Research paper thumbnail of Design and Optimization of Neuro-Fuzzy-Based Recognition of Musical Rhythm Patterns

International Journal of Smart Engineering System Design, 2003

Research paper thumbnail of A Distributed Model For Multiple-Viewpoint Melodic Prediction

International Symposium/Conference on Music Information Retrieval, 2013

Research paper thumbnail of Evaluation of Fake News Detection with Knowledge-Enhanced Language Models

Proceedings of the International AAAI Conference on Web and Social Media, May 31, 2022

Research paper thumbnail of Joint Singing Voice Separation and F0 Estimation with Deep U-Net Architectures

Research paper thumbnail of Understandability of Global Post-hoc Explanations of Black-box Models: Dataset and Analysis

The dataset contains the data collected in a user study carried out to evaluate the impact of usi... more The dataset contains the data collected in a user study carried out to evaluate the impact of using domain knowledge, ontologies, in the creation of global post-hoc explanations of black-box models. The research hypothesis was that the use of ontologies could enhance the understandability of explanations by humans. To validate this research hypothesis we ran a user study where participants were asked to carry out several tasks. In each task, the answers, time of response, and user understandability and confidence were collected and measured. The data analysis revealed that the use of ontologies do enhance the understandability of explanations of black-box models by human users, in particular, in the form of decision trees explaining artificial neural networks.

Research paper thumbnail of Multiple Viewpiont Melodic Prediction with Fixed-Context Neural Networks

International Symposium/Conference on Music Information Retrieval, 2014

Research paper thumbnail of Perceiving and predicting expressive rhythm with recurrent neural networks

Research paper thumbnail of Melodic structure and automatic classification in Bach's 2-part inventions

Research paper thumbnail of Hybrid Long- and Short-Term Models of Folk Melodies

International Symposium/Conference on Music Information Retrieval, 2015

Research paper thumbnail of Opuscope - Towards a Corpus-Based Music Repository

International Symposium/Conference on Music Information Retrieval, 2002

Research paper thumbnail of Studying the Effect of Metre Perception on Rhythm and Melody Modelling with LSTMs

Zenodo (CERN European Organization for Nuclear Research), Oct 4, 2014

Research paper thumbnail of The Influence of Pitch on Melodic Segmentation

International Symposium/Conference on Music Information Retrieval, 2004

Research paper thumbnail of A Wavelet-Based Approach to Pattern Discovery in Melodies

Springer eBooks, Oct 28, 2015

Research paper thumbnail of Concepts of the MUSITECH infrastructure for Internet-based interactive musical applications

Research paper thumbnail of Efficient Melody Retrieval with Motif Contour Classes

International Symposium/Conference on Music Information Retrieval, 2005

Research paper thumbnail of NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection

arXiv (Cornell University), May 22, 2023

Research paper thumbnail of Integrating Convexity and Compactness into the ISSM: Melodic Analysis of Music

Research paper thumbnail of Learned complex masks for multi-instrument source separation

arXiv (Cornell University), Mar 23, 2021

Research paper thumbnail of Anti-Transfer Learning for Task Invariance in Convolutional Neural Networks for Speech Processing

arXiv (Cornell University), Jun 11, 2020

Research paper thumbnail of Learning Speech Emotion Representations in the Quaternion Domain

arXiv (Cornell University), Apr 5, 2022

Research paper thumbnail of Design and Optimization of Neuro-Fuzzy-Based Recognition of Musical Rhythm Patterns

International Journal of Smart Engineering System Design, 2003

Research paper thumbnail of A Distributed Model For Multiple-Viewpoint Melodic Prediction

International Symposium/Conference on Music Information Retrieval, 2013

Research paper thumbnail of Evaluation of Fake News Detection with Knowledge-Enhanced Language Models

Proceedings of the International AAAI Conference on Web and Social Media, May 31, 2022

Research paper thumbnail of Joint Singing Voice Separation and F0 Estimation with Deep U-Net Architectures

Log In