Home /
Research
Showing 295 - 300 / 904
Neural Representations for Modeling Variation in English Speech
MartijnBartelds, WietsedeVries, FarazSanal....
Published date-11/25/2020
Variation in speech is often represented and investigated using phonetic transcriptions, but transcribing speech is time-consuming and error prone. To create reliable representations of speech independent from phonetic transcriptions, we …
Simple statistical methods for unsupervised brain anomaly detection on MRI are competitive to deep learning methods
VictorSaase, HolgerWenz, ThomasGanslandt....
Published date-11/25/2020
AnomalyDetection
Statistical analysis of magnetic resonance imaging (MRI) can help radiologists to detect pathologies that are otherwise likely to be missed. Deep learning (DL) has shown promise in modeling complex spatial …
BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning
KamilDeja, PawełWawrzyński, DanielMarczak....
Published date-11/25/2020
ContinualLearning
We introduce a binary latent space autoencoder architecture to rehearse training samples for the continual learning of neural networks. The ability to extend the knowledge of a model with new …
Learning Curves for Drug Response Prediction in Cancer Cell Lines
AlexanderPartin, ThomasBrettin, YvonneA.Evrard....
Published date-11/25/2020
Motivated by the size of cell line drug sensitivity data, researchers have been developing machine learning (ML) models for predicting drug response to advance cancer treatment. As drug sensitivity studies …
An end-to-end data-driven optimisation framework for constrained trajectories
FlorentDewez, BenjaminGuedj, ArthurTalpaert....
Published date-11/24/2020
Many real-world problems require to optimise trajectories under constraints. Classical approaches are based on optimal control methods but require an exact knowledge of the underlying dynamics, which could be challenging …
Dual Supervision Framework for Relation Extraction with Distant Supervision and Human Annotation
WoohwanJung, KyuseokShim....
Published date-11/24/2020
RelationExtraction
Relation extraction (RE) has been extensively studied due to its importance in real-world applications such as knowledge base construction and question answering. Most of the existing works train the models …