23 papers · ranked by Valyu relevance
Filip Ilievski, Barbara Hammer, Frank van Harmelen, Benjamin Paaßen + 21 more
'Sascha Saralajew' 'Ute Schmid' 'Michael Biehl' 'Marianna Bolognesi' 'Xin Dong' 'Kiril Gashteovski' 'Pascal Hitzler' 'Giuseppe Marra' 'Pasquale Minervini' 'Martin Mundt' 'Axel-Cyrille Ngonga Ngomo' 'Alessandro Oltramari' 'Gabriella Pasi' 'Zeynep G. Saribatur' 'Luciano Serafini' 'John Shawe‐Taylor' 'Vered Shwartz'…
Mengqing Huang, Hongchuan Yu, Jianjun Zhang
There is an ongoing and dedicated effort to estimate bounds on the generalization error of deep learning models, coupled with an increasing interest with practical metrics that can be used to experimentally evaluate a model’s ability to generalize. This interest is not only driven by practical considerations but is…
Chenxiao Yang, Zhiyuan Li, Shai Ben-David, Nathan Srebro
We study hierarchical domain generalization as a problem of extrapolation from finite observed regions to an entire instance space, replacing i.i.d. sampling with arbitrary domain hierarchies. We show that the central obstruction is not only the complexity of the hypothesis class, but the train/test domain partition…
Daniel Reißner, Abel Armas-Cervantes, Marcello La Rosa
- A framework of generalization measures is defined in the field of automated process discovery that relates patterns of process behavior identified from an event log to the control-flow structures of a process model. - The framework is instantiated with a generalization measure that tests the repetitive and concurrent…
Jiwon Park, Dongil Chung
People often use recognizable features to infer the value of novel consumables. This “generalization” strategy is known to be beneficial in stable environments, such that individuals can use previously learned rules and values in efficiently exploring new situations. However, it remains unclear whether and how…
Ella Bar, Max Bringmann, Gennadiy Belonosov, Kristoffer Aberg + 3 more
Overgeneralization of negative experiences, in which aversive responses spread to otherwise safe stimuli, often co-occurs with sleep disruption, and both are central features of anxiety and posttraumatic stress disorder (PTSD). Here, we show that sleep shifts emotional generalization away from the negative and toward…
Shuge Wang, Vera Vasas, Laura Freeland, Daniel Osorio + 1 more
'Elisabetta Versace'] Title: Summary Inductive generalization is adaptive in novel contexts for both biological and artificial intelligence. Spontaneous generalization in inexperienced animals raises questions on whether predispositions (evolutionarily acquired biases, or priors) enable generalization from sparse data…
Eleanor Stansbury, Arnaud Witt, Patrick Bard, Jean-Pierre Thibaut + 1 more
'Antoine Coutrot'] Recent research has shown that comparisons of multiple learning stimuli which are associated with the same novel noun favor taxonomic generalization of this noun. These findings contrast with single-stimulus learning in which children follow so-called lexical biases. However, little is known about…
Elies Gil-Fuster, Jens Eisert, Carlos Bravo-Prieto
Quantum machine learning models have shown successful generalization performance even when trained with few data. In this work, through systematic randomization experiments, we show that traditional approaches to understanding generalization fail to explain the behavior of such quantum models. Our experiments reveal…
Charu Manivannan, Jakub Krukar, Angela Schwering, Saeid Norouzian-Maleki
'Saeid Norouzian-Maleki'] Sketch maps are valuable tools used across various disciplines including spatial cognition, environmental psychology, and spatial reasoning. A common approach to evaluate sketch maps in research is to align and compare them with metric maps. However, sketch maps are highly abstract and contain…
Samuel Lippl, Kenneth Kay, Greg Jensen, Vincent P. Ferrera + 1 more
Humans and animals routinely infer relations between different items or events and generalize these relations to novel combinations of items (“compositional generalization”). This allows them to respond appropriately to radically novel circumstances and is fundamental to advanced cognition. However, how learning…
Binhang Qi, Yun Lin, Xinyi Weng, Chenyan Liu + 3 more
Test cases are essential for software development and maintenance. In practice, developers derive multiple test cases from an implicit pattern based on their understanding of requirements and inference of diverse test scenarios, each validating a specific behavior of the focal method. However, producing comprehensive…
Woo-Tek Lee, Eliot Hazeltine, Jiefeng Jiang
Task knowledge is encoded hierarchically such that complex tasks are composed of simpler tasks. This compositional organization also supports generalization to facilitate learning of related but novel complex tasks. To study how the brain implements composition and generalization in hierarchical task learning, we…
Johann Glock, Clemens Bauer, Martin Pinzger
Conventional unit tests validate single input-output pairs, leaving most inputs of an execution path untested. Property-based testing addresses this shortcoming by generating multiple inputs satisfying properties but requires significant manual effort to define properties and their constraints. We propose a…
Florian Sandhaeger, Markus Siegel
Title: Highlights 1. • Multivariate pattern generalization is commonly used to assess the similarity of neural representations between contexts. 2. • When applied to neural mass signals such as LFP, MEG or fMRI, pattern generalization is susceptible to confounds due to spatial mixing. 3. • Statistically significant…
Gabriele Sacco, Loris Bozzato, Oliver Kutz
Representation Authors: ['Gabriele Sacco' 'Loris Bozzato' 'Oliver Kutz'] > Abstract. Defeasible reasoning is a kind of reasoning where some generalisations may not be valid in all circumstances, that is general conclusions may fail in some cases. Various formalisms have been developed to model this kind of reasoning…
Itamar Lerner, Praveen K. Pilly, Ahmed A. Moustafa
Contemporary research of sleep in humans and animals repeatedly show its involvement in memory consolidation (Rasch and Born, [11]). While early studies in the field were mostly concerned with the way sleep strengthens existing memories and skills (e.g., Plihal and Born, [10]), it has since become clear that…
Alba Lopez-Moraga, Zeynep Gültekin, Laura Luyten, Tom Beckers
Generalization of conditioned fear is adaptive for survival. However, overgeneralization of fear from threat cues to loosely similar yet safe stimuli is a hallmark of anxiety-related disorders. Such overgeneralization may moreover impact other fear learning processes. In particular, broad fear generalization might…
Yu Zhang, Jinhui Yu, Hongwei Song, Minghui Yang
Accurate determination of reaction rate constants in the combustion circumstance is very challenging both experimentally and theoretically. In this work, three supervised machine learning algorithms, including XGB, FNN and XGB-FNN, are used to develop quantitative structure−property relationship models for the…
Authors not listed
Identifying synthesis routes from knowledge graphs poses challenges beyond retrosynthesis, including path–finding artifacts and data issues. We introduce “SynGPS”, a novel algorithm that overcomes these limitations by identifying viable routes even with common artifacts. SynGPS can resolve nonsensical cycles…
Matthijs van Veelen
The generality of Hamilton’s rule^1,2^ is much debated^3–14^. In this paper, I show that this debate can be resolved by constructing a general version of Hamilton’s rule, which allows for a large variety of ways in which the fitness of an individual can depend on the social behaviour of oneself and of others. For this…
Yasmine Nahal, Janosch Menke, Julien Martinelli, Markus Heinonen + 5 more
Machine learning (ML) systems have enabled the modelling of quantitative structure-property relationships (QSPR) and structure-activity relationships (QSAR) using existing experimental data to predict target properties for new molecules. These property predictors hold significant potential in accelerating drug…
Authors not listed
Step-by-step thinking is essential in all domains of chemical sciences and engineering. While machine learning tools are broadly used, algorithms that automate reasoning are far less common. We elaborate on seven categories of human reasoning activities and connect each to applications in chemical science and…