Search Results for author:
Found 7 papers, 3 papers with code
ConstraintMatch for Semi-constrained Clustering
Constrained clustering allows the training of classification models using pairwise constraints only, which are weak and relatively easy to mine, while still yielding full-supervision-level model performance.
Approximately Bayes-Optimal Pseudo Label Selection
We derive this selection criterion by proving Bayes optimality of the posterior predictive of pseudo-samples.
Multimodal Deep Learning
This book is the result of a seminar in which we reviewed multimodal approaches and attempted to create a solid overview of the field, starting with the current state-of-the-art approaches in the two subfields of Deep Learning individually.
Uncertainty-aware Pseudo-label Selection for Positive-Unlabeled Learning
In this work, we thus propose to tackle the issues of imbalanced datasets and model calibration in a PUL setting through an uncertainty-aware pseudo-labeling procedure (PUUPL): by boosting the signal from the minority class, pseudo-labeling expands the labeled dataset with new samples from the unlabeled set, while explicit uncertainty quantification prevents the emergence of harmful confirmation bias leading to increased predictive performance.
Deep Semi-Supervised Learning for Time Series Classification
Based on these adaptations, we explore the potential of deep semi-supervised learning in the context of time series classification by evaluating our methods on large public time series classification problems with varying amounts of labelled samples.
Granular Motor State Monitoring of Free Living Parkinson's Disease Patients via Deep Learning
Parkinson's disease (PD) is the second most common neurodegenerative disease worldwide and affects around 1% of the (60+ years old) elderly population in industrial nations.
Wearable-based Parkinson's Disease Severity Monitoring using Deep Learning
To solve the problem of limited availability of high quality training data, we propose a transfer learning technique which helps to improve model performance substantially.
