Search Results for author: Twan van Laarhoven

Found 16 papers, 4 papers with code

Going Grayscale: The Road to Understanding and Improving Unlearnable Examples

1 code implementation25 Nov 2021 Zhuoran Liu, Zhengyu Zhao, Alex Kolmus, Tijn Berns, Twan van Laarhoven, Tom Heskes, Martha Larson

Recent work has shown that imperceptible perturbations can be applied to craft unlearnable examples (ULEs), i. e. images whose content cannot be used to improve a classifier during training.

Swift sky localization of gravitational waves using deep learning seeded importance sampling

1 code implementation1 Nov 2021 Alex Kolmus, Grégory Baltus, Justin Janquart, Twan van Laarhoven, Sarah Caudill, Tom Heskes

Fast, highly accurate, and reliable inference of the sky origin of gravitational waves would enable real-time multi-messenger astronomy.

Bayesian Inference

Gaussian Processes with Skewed Laplace Spectral Mixture Kernels for Long-term Forecasting

no code implementations8 Nov 2020 Kai Chen, Twan van Laarhoven, Elena Marchiori

The heavy tail and skewness characteristics of such distributions in the spectral domain allow to capture long-range covariance of the signal in the time domain.

Gaussian Processes Time Series

Unsupervised Domain Adaptation using Graph Transduction Games

no code implementations6 May 2019 Sebastiano Vascon, Sinem Aslan, Alessandro Torcinovich, Twan van Laarhoven, Elena Marchiori, Marcello Pelillo

Unsupervised domain adaptation (UDA) amounts to assigning class labels to the unlabeled instances of a dataset from a target domain, using labeled instances of a dataset from a related source domain.

Object Recognition Unsupervised Domain Adaptation

Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation

no code implementations12 Apr 2018 Jeroen Manders, Twan van Laarhoven, Elena Marchiori

Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adaptation reduces to aligning source and target domain at class prediction uncertainty level.

Image Classification Unsupervised Domain Adaptation

Generative models for local network community detection

1 code implementation12 Apr 2018 Twan van Laarhoven

By assuming that the network is uniform, we can approximate the structure of unobserved parts of the network to obtain a method for local community detection.

Local Community Detection Stochastic Block Model

Domain Adaptation with Randomized Expectation Maximization

1 code implementation20 Mar 2018 Twan van Laarhoven, Elena Marchiori

Despite their success, state of the art methods based on this approach are either involved or unable to directly scale to data with many features.

Domain Adaptation Transfer Learning

Deep Learning for Automatic Stereotypical Motor Movement Detection using Wearable Sensors in Autism Spectrum Disorders

no code implementations14 Sep 2017 Nastaran Mohammadian Rad, Seyed Mostafa Kia, Calogero Zarbo, Twan van Laarhoven, Giuseppe Jurman, Paola Venuti, Elena Marchiori, Cesare Furlanello

Our results show that: 1) feature learning outperforms handcrafted features; 2) parameter transfer learning is beneficial in longitudinal settings; 3) using LSTM to learn the temporal dynamic of signals enhances the detection rate especially for skewed training data; 4) an ensemble of LSTMs provides more accurate and stable detectors.

Ensemble Learning Transfer Learning

Unsupervised Domain Adaptation with Random Walks on Target Labelings

no code implementations16 Jun 2017 Twan van Laarhoven, Elena Marchiori

Unsupervised Domain Adaptation (DA) is used to automatize the task of labeling data: an unlabeled dataset (target) is annotated using a labeled dataset (source) from a related domain.

Unsupervised Domain Adaptation

L2 Regularization versus Batch and Weight Normalization

no code implementations16 Jun 2017 Twan van Laarhoven

We show that popular optimization methods such as ADAM only partially eliminate the influence of normalization on the learning rate.

L2 Regularization

Local Network Community Detection with Continuous Optimization of Conductance and Weighted Kernel K-Means

no code implementations21 Jan 2016 Twan van Laarhoven, Elena Marchiori

We investigate the relation of conductance with weighted kernel k-means for a single community, which leads to the introduction of a new objective function, $\sigma$-conductance.

Local Community Detection

Resolution-limit-free and local Non-negative Matrix Factorization quality functions for graph clustering

no code implementations22 Jul 2014 Twan van Laarhoven, Elena Marchiori

We argue that this is a desirable property, provide conditions under which NMF quality functions are local, and propose a novel class of local probabilistic NMF quality functions for soft graph clustering.

Graph Clustering graph partitioning

Axioms for graph clustering quality functions

no code implementations15 Aug 2013 Twan van Laarhoven, Elena Marchiori

This motivates the derivation of a new family of quality functions, adaptive scale modularity, which does satisfy the proposed axioms.

Community Detection Graph Clustering

Cannot find the paper you are looking for? You can Submit a new open access paper.