31 citations · 151 across the 20 of their papers we have counts for
24 papers
Revisiting the Robustness of the Minimum Error Entropy Criterion: A Transfer Learning Case Study
Luis Pedro Silvestrin, Shujian Yu, Mark Hoogendoorn
Coping with distributional shifts is an important part of transfer learning methods in order to perform well in real-life tasks. However, most of the existing approaches in this ar…
Multivariate Time Series Early Classification Across Channel and Time Dimensions
Leonardos Pantiskas, Kees Verstoep, Mark Hoogendoorn +1
Nowadays, the deployment of deep learning models on edge devices for addressing real-world classification problems is becoming more prevalent. Moreover, there is a growing populari…
Modelling Long Range Dependencies in D: From Task-Specific to a General Purpose CNN
David M. Knigge, David W. Romero, Albert Gu +5
Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data. In…
Improving generalization in reinforcement learning through forked agents
Olivier Moulin, Vincent Francois-Lavet, Mark Hoogendoorn
An eco-system of agents each having their own policy with some, but limited, generalizability has proven to be a reliable approach to increase generalization across procedurally ge…
Disentangled (Un)Controllable Features
Jacob E. Kooi, Mark Hoogendoorn, Vincent François-Lavet
In the context of MDPs with high-dimensional states, downstream tasks are predominantly applied on a compressed, low-dimensional representation of the original input space. A varie…
An Empirical Evaluation of Multivariate Time Series Classification with Input Transformation across Different Dimensions
Leonardos Pantiskas, Kees Verstoep, Mark Hoogendoorn +1
In current research, machine and deep learning solutions for the classification of temporal data are shifting from single-channel datasets (univariate) to problems with multiple ch…
Towards a General Purpose CNN for Long Range Dependencies in D
David W. Romero, David M. Knigge, Albert Gu +4
The use of Convolutional Neural Networks (CNNs) is widespread in Deep Learning due to a range of desirable model properties which result in an efficient and effective machine learn…
Taking ROCKET on an Efficiency Mission: Multivariate Time Series Classification with LightWaveS
Leonardos Pantiskas, Kees Verstoep, Mark Hoogendoorn +1
Nowadays, with the rising number of sensors in sectors such as healthcare and industry, the problem of multivariate time series classification (MTSC) is getting increasingly releva…
Improving generalization to new environments and removing catastrophic forgetting in Reinforcement Learning by using an eco-system of agents
Olivier Moulin, Vincent Francois-Lavet, Paul Elbers +1
Adapting a Reinforcement Learning (RL) agent to an unseen environment is a difficult task due to typical over-fitting on the training environment. RL agents are often capable of so…
The Dutch Draw: Constructing a Universal Baseline for Binary Prediction Models
Etienne van de Bijl, Jan Klein, Joris Pries +3
Novel prediction methods should always be compared to a baseline to know how well they perform. Without this frame of reference, the performance score of a model is basically meani…
Transfer-Learning Across Datasets with Different Input Dimensions: An Algorithm and Analysis for the Linear Regression Case
Luis Pedro Silvestrin, Harry van Zanten, Mark Hoogendoorn +1
With the development of new sensors and monitoring devices, more sources of data become available to be used as inputs for machine learning models. These can on the one hand help t…
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
David W. Romero, Robert-Jan Bruintjes, Jakub M. Tomczak +3
When designing Convolutional Neural Networks (CNNs), one must select the size\break of the convolutional kernels before training. Recent works show CNNs benefit from different kern…
Jasmine: A New Active Learning Approach to Combat Cybercrime
Jan Klein, Sandjai Bhulai, Mark Hoogendoorn +1
Over the past decade, the advent of cybercrime has accelarated the research on cybersecurity. However, the deployment of intrusion detection methods falls short. One of the reasons…
A Framework for Imbalanced Time-series Forecasting
Luis P. Silvestrin, Leonardos Pantiskas, Mark Hoogendoorn
Time-series forecasting plays an important role in many domains. Boosted by the advances in Deep Learning algorithms, it has for instance been used to predict wind power for eolic…
pH-RL: A personalization architecture to bring reinforcement learning to health practice
Ali el Hassouni, Mark Hoogendoorn, Marketa Ciharova +5
While reinforcement learning (RL) has proven to be the approach of choice for tackling many complex problems, it remains challenging to develop and deploy RL agents in real-life sc…
CKConv: Continuous Kernel Convolution For Sequential Data
David W. Romero, Anna Kuzina, Erik J. Bekkers +2
Conventional neural architectures for sequential data present important limitations. Recurrent networks suffer from exploding and vanishing gradients, small effective memory horizo…
Mixing Consistent Deep Clustering
Daniel Lutscher, Ali el Hassouni, Maarten Stol +1
Finding well-defined clusters in data represents a fundamental challenge for many data-driven applications, and largely depends on good data representation. Drawing on literature r…
Attentive Group Equivariant Convolutional Networks
David W. Romero, Erik J. Bekkers, Jakub M. Tomczak +1
Although group convolutional networks are able to learn powerful representations based on symmetry patterns, they lack explicit means to learn meaningful relationships among them (…
Trace Clustering on Very Large Event Data in Healthcare Using Frequent Sequence Patterns
Xixi Lu, Seyed Amin Tabatabaei, Mark Hoogendoorn +1
Trace clustering has increasingly been applied to find homogenous process executions. However, current techniques have difficulties in finding a meaningful and insightful clusterin…
Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data
David W. Romero, Mark Hoogendoorn
Equivariance is a nice property to have as it produces much more parameter efficient neural architectures and preserves the structure of the input through the feature mapping. Even…
Reinforcement Learning for Personalized Dialogue Management
Floris den Hengst, Mark Hoogendoorn, Frank van Harmelen +1
Language systems have been of great interest to the research community and have recently reached the mass market through various assistant platforms on the web. Reinforcement Learn…
GP-HD: Using Genetic Programming to Generate Dynamical Systems Models for Health Care
Mark Hoogendoorn, Ward van Breda, Jeroen Ruwaard
The huge wealth of data in the health domain can be exploited to create models that predict development of health states over time. Temporal learning algorithms are well suited to…
Identifying Patient Groups based on Frequent Patterns of Patient Samples
Seyed Amin Tabatabaei, Xixi Lu, Mark Hoogendoorn +1
Grouping patients meaningfully can give insights about the different types of patients, their needs, and the priorities. Finding groups that are meaningful is however very challeng…
A clustering-based reinforcement learning approach for tailored personalization of e-Health interventions
Ali el Hassouni, Mark Hoogendoorn, Martijn van Otterlo +3
Personalization is very powerful in improving the effectiveness of health interventions. Reinforcement learning (RL) algorithms are suitable for learning these tailored interventio…