Search Results for author:
Found 25 papers, 7 papers with code
Improved Data Generation for Enhanced Asset Allocation: A Synthetic Dataset Approach for the Fixed Income Universe
We present a novel process for generating synthetic datasets tailored to assess asset allocation methods and construct portfolios within the fixed income universe.
NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection
NeSy4VRD is a multifaceted resource designed to support the development of neurosymbolic AI (NeSy) research.
Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks
We conduct a theoretical analysis of linear RNNs and identify conditions for the models to exhibit exact counting behaviour.
Towards a Unified Model for Generating Answers and Explanations in Visual Question Answering
The field of visual question answering (VQA) has recently seen a surge in research focused on providing explanations for predicted answers.
Exploring the Long-Term Generalization of Counting Behavior in RNNs
Despite this and some positive empirical results for LSTMs on Dyck-1 languages, our experimental results show that LSTMs fail to learn correct counting behavior for sequences that are significantly longer than in the training data.
The Beyond the Fence Musical and Computer Says Show Documentary
During 2015 and early 2016, the cultural application of Computational Creativity research and practice took a big leap forward, with a project where multiple computational systems were used to provide advice and material for a new musical theatre production.
Learning Speech Emotion Representations in the Quaternion Domain
On the one hand, the classifier permits to optimize each latent axis of the embeddings for the classification of a specific emotion-related characteristic: valence, arousal, dominance and overall emotion.
Evaluation of Fake News Detection with Knowledge-Enhanced Language Models
The predominant state-of-the-art approaches are based on fine-tuning PLMs on labelled fake news datasets.
Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modelling
Abstract patterns are the best known examples of a hard problem for neural networks in terms of generalisation to unseen data.
Anti-Transfer Learning for Task Invariance in Convolutional Neural Networks for Speech Processing
While transfer learning assumes that the learning process for a target task will benefit from re-using representations learned for another task, anti-transfer avoids the learning of representations that have been learned for an orthogonal task, i. e., one that is not relevant and potentially misleading for the target task, such as speaker identity for speech recognition or speech content for emotion recognition.
Weight Priors for Learning Identity Relations
In this work, we extend RBP by realizing it as a Bayesian prior on network weights to model the identity relations.
Multi-Time-Scale Convolution for Emotion Recognition from Speech Audio Signals
We evaluate MTS and standard convolutional layers in different architectures for emotion recognition from speech audio, using 4 datasets of different sizes.
Making Good on LSTMs' Unfulfilled Promise
We examine an alternative called Continual Learning (CL), a memory-augmented approach, which can provide transparent explanations, i. e. which memory did what and when.
Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical Energy
In recent years, deep learning has surpassed traditional approaches to the problem of singing voice separation.
Trepan Reloaded: A Knowledge-driven Approach to Explaining Artificial Neural Networks
Whilst a plethora of approaches have been developed for post-hoc explainability, only a few focus on how to use domain knowledge, and how this influences the understandability of global explanations from the users' perspective.
Factors for the Generalisation of Identity Relations by Neural Networks
In this work we explore various factors in the neural network architecture and learning process whether they make a difference to the generalisation on equality detection of Neural Networks without and and with DR units in early and mid fusion architectures.
Continual Learning Augmented Investment Decisions
Investment decisions can benefit from incorporating an accumulated knowledge of the past to drive future decision making.
Modelling Identity Rules with Neural Networks
We propose a new approach to modify standard neural network architectures, called Relation Based Patterns (RBP) with different variants for classification and prediction.
Feed-Forward Neural Networks Need Inductive Bias to Learn Equality Relations
The DR units create an inductive bias in the networks, so that they do learn to generalise, even from small numbers of examples and we have not found any negative effect of their inclusion in the network.
Improved Speech Enhancement with the Wave-U-Net
We study the use of the Wave-U-Net architecture for speech enhancement, a model introduced by Stoller et al for the separation of music vocals and accompaniment.
Ranked #24 on
Speech Enhancement
on VoiceBank + DEMAND
M2U-Net: Effective and Efficient Retinal Vessel Segmentation for Resource-Constrained Environments
In this paper, we present a novel neural network architecture for retinal vessel segmentation that improves over the state of the art on two benchmark datasets, is the first to run in real time on high resolution images, and its small memory and processing requirements make it deployable in mobile and embedded systems.
Singing Voice Separation with Deep U-Net Convolutional Networks
The decomposition of a music audio signal into its vocal and backing track components is analogous to image-toimage translation, where a mixed spectrogram is transformed into its constituent sources.
Ranked #1 on
Speech Separation
on iKala
Linear-Time Sequence Classification using Restricted Boltzmann Machines
Also, the experimental results on optical character recognition, part-of-speech tagging and text chunking demonstrate that our model is comparable to recurrent neural networks with complex memory gates while requiring far fewer parameters.
Generalising the Discriminative Restricted Boltzmann Machine
Results show that each of the three compared models outperforms the remaining two in one of the three datasets, thus indicating that the proposed theoretical generalisation of the DRBM may be valuable in practice.
A Hybrid Recurrent Neural Network For Music Transcription
We investigate the problem of incorporating higher-level symbolic score-like information into Automatic Music Transcription (AMT) systems to improve their performance.
