55 citations · 186 across the 31 of their papers we have counts for
17 papers · 1 filter
An approach to melodic segmentation and classification based on filtering with the Haar-wavelet
Gissel Velarde, Tillman Weyde, David Meredith
We present a novel method of classification and segmentation of melodies in symbolic representation. The method is based on filtering pitch as a signal over time with the Haar-wave…
Wavelet-Filtering of Symbolic Music Representations for Folk Tune Segmentation and Classification
Gissel Velarde, Tillman Weyde, David Meredith
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 fil…
When to Accept Automated Predictions and When to Defer to Human Judgment?
Daniel Sikar, Artur Garcez, Tillman Weyde +2
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. Thi…
The Misclassification Likelihood Matrix: Some Classes Are More Likely To Be Misclassified Than Others
Daniel Sikar, Artur Garcez, Robin Bloomfield +6
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…
Derivative-based regularization for regression
Enrico Lopedoto, Maksim Shekhunov, Vitaly Aksenov +2
In this work, we introduce a novel approach to regularization in multivariable regression problems. Our regularizer, called DLoss, penalises differences between the model's derivat…
Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks
Nadine El-Naggar, Pranava Madhyastha, Tillman Weyde
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…
Anti-Transfer Learning for Task Invariance in Convolutional Neural Networks for Speech Processing
Eric Guizzo, Tillman Weyde, Giacomo Tarroni
We introduce the novel concept of anti-transfer learning for speech processing with convolutional neural networks. While transfer learning assumes that the learning process for a t…
Weight Priors for Learning Identity Relations
Radha Kopparti, Tillman Weyde
Learning abstract and systematic relations has been an open issue in neural network learning for over 30 years. It has been shown recently that neural networks do not learn relatio…
Making Good on LSTMs' Unfulfilled Promise
Daniel Philps, Artur d'Avila Garcez, Tillman Weyde
LSTMs promise much to financial time-series analysis, temporal and cross-sectional inference, but we find that they do not deliver in a real-world financial management task. We exa…
Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical Energy
Joaquin Perez-Lapillo, Oleksandr Galkin, Tillman Weyde
In recent years, deep learning has surpassed traditional approaches to the problem of singing voice separation. The Wave-U-Net is a recent deep network architecture that operates d…
Factors for the Generalisation of Identity Relations by Neural Networks
Radha Kopparti, Tillman Weyde
Many researchers implicitly assume that neural networks learn relations and generalise them to new unseen data. It has been shown recently, however, that the generalisation of feed…
Continual Learning Augmented Investment Decisions
Daniel Philps, Tillman Weyde, Artur d'Avila Garcez +1
Investment decisions can benefit from incorporating an accumulated knowledge of the past to drive future decision making. We introduce Continual Learning Augmentation (CLA) which i…
Feed-Forward Neural Networks Need Inductive Bias to Learn Equality Relations
Tillman Weyde, Radha Manisha Kopparti
Basic binary relations such as equality and inequality are fundamental to relational data structures. Neural networks should learn such relations and generalise to new unseen data.…
Modelling Identity Rules with Neural Networks
Tillman Weyde, Radha Manisha Kopparti
In this paper, we show that standard feed-forward and recurrent neural networks fail to learn abstract patterns based on identity rules. We propose Relation Based Pattern (RBP) ext…
Linear-Time Sequence Classification using Restricted Boltzmann Machines
Son N. Tran, Srikanth Cherla, Artur Garcez +1
Classification of sequence data is the topic of interest for dynamic Bayesian models and Recurrent Neural Networks (RNNs). While the former can explicitly model the temporal depend…
Generalising the Discriminative Restricted Boltzmann Machine
Srikanth Cherla, Son N Tran, Tillman Weyde +1
We present a novel theoretical result that generalises the Discriminative Restricted Boltzmann Machine (DRBM). While originally the DRBM was defined assuming the {0, 1}-Bernoulli d…
A Hybrid Recurrent Neural Network For Music Transcription
Siddharth Sigtia, Emmanouil Benetos, Nicolas Boulanger-Lewandowski +3
We investigate the problem of incorporating higher-level symbolic score-like information into Automatic Music Transcription (AMT) systems to improve their performance. We use recur…