374 citations · 700 across the 13 of their papers we have counts for
15 papers
Heterogeneous Structured Pruning Under Resource Constraints for Hardware-Efficient Large Language Models
Cameron Barker, Andreas Paraskeva, Jan N. van Rijn +2
Training-free pruning removes weights from pretrained large language models to reduce their deployment cost. However, existing approaches typically consider only the total number o…
Render Before Reading: Visual Rendering as a Prompt Injection Defense
Jie Zhang, Andrei Baroian, Jan N. van Rijn +2
Large language models are vulnerable to prompt injection attacks, where third-party adversarial content can hijack the model's behavior. In this paper, we study the role played by…
Exploring Solver-Level Warmstarting for Neural Network Verification
Annelot Bosman, Minghao Liu, Marta Kwiatkowska +2
Neural network verification has become a key tool for providing formal guarantees on the behaviour of neural networks. However, many verification problems remain computationally in…
Evolving Executable Pipeline Programs for AutoML with Language Models
Sofoklis Kitharidis, Cor J. Veenman, Jan N. van Rijn +2
Automated machine learning (AutoML) systems search for pipelines within a space of preprocessing operators, learners, and hyper-parameters specified in advance: they can select and…
Finding Patterns in Ambiguity: Interpretable Stress Testing in the Decision~Boundary
Inês Gomes, Luís F. Teixeira, Jan N. van Rijn +4
The increasing use of deep learning across various domains highlights the importance of understanding the decision-making processes of these black-box models. Recent research focus…
Automated Design of Linear Bounding Functions for Sigmoidal Nonlinearities in Neural Networks
Matthias König, Xiyue Zhang, Holger H. Hoos +2
The ubiquity of deep learning algorithms in various applications has amplified the need for assuring their robustness against small input perturbations such as those occurring in a…
Are LSTMs Good Few-Shot Learners?
Mike Huisman, Thomas M. Moerland, Aske Plaat +1
Deep learning requires large amounts of data to learn new tasks well, limiting its applicability to domains where such data is available. Meta-learning overcomes this limitation by…
Subspace Adaptation Prior for Few-Shot Learning
Mike Huisman, Aske Plaat, Jan N. van Rijn
Gradient-based meta-learning techniques aim to distill useful prior knowledge from a set of training tasks such that new tasks can be learned more efficiently with gradient descent…
Understanding Transfer Learning and Gradient-Based Meta-Learning Techniques
Mike Huisman, Aske Plaat, Jan N. van Rijn
Deep neural networks can yield good performance on various tasks but often require large amounts of data to train them. Meta-learning received considerable attention as one approac…
Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward
Devis Tuia, Konrad Schindler, Begüm Demir +11
Earth observation (EO) is a prime instrument for monitoring land and ocean processes, studying the dynamics at work, and taking the pulse of our planet. This article gives a bird's…
Learning Curves for Decision Making in Supervised Machine Learning: A Survey
Felix Mohr, Jan N. van Rijn
Learning curves are a concept from social sciences that has been adopted in the context of machine learning to assess the performance of a learning algorithm with respect to a cert…
Fast and Informative Model Selection using Learning Curve Cross-Validation
Felix Mohr, Jan N. van Rijn
Common cross-validation (CV) methods like k-fold cross-validation or Monte-Carlo cross-validation estimate the predictive performance of a learner by repeatedly training it on a la…
Stateless Neural Meta-Learning using Second-Order Gradients
Mike Huisman, Aske Plaat, Jan N. van Rijn
Deep learning typically requires large data sets and much compute power for each new problem that is learned. Meta-learning can be used to learn a good prior that facilitates quick…
A Survey of Deep Meta-Learning
Mike Huisman, Jan N. van Rijn, Aske Plaat
Deep neural networks can achieve great successes when presented with large data sets and sufficient computational resources. However, their ability to learn new concepts quickly is…
Hyperparameter Importance Across Datasets
J. N. van Rijn, F. Hutter
With the advent of automated machine learning, automated hyperparameter optimization methods are by now routinely used in data mining. However, this progress is not yet matched by…