We consider the problem of learning multiple tasks in a continual learning setting in which data from different tasks is presented to the learner in a streaming fashion. A key challenge in this... Show moreWe consider the problem of learning multiple tasks in a continual learning setting in which data from different tasks is presented to the learner in a streaming fashion. A key challenge in this setting is the so-called "catastrophic forgetting problem", in which the performance of the learner in an "old task" decreases when subsequently trained on a "new task". Existing continual learning methods, such as Averaged Gradient Episodic Memory (A-GEM) and Orthogonal Gradient Descent (OGD), address catastrophic forgetting by minimizing the loss for the current task without increasing the loss for previous tasks. However, these methods assume the learner knows when the task changes, which is unrealistic in practice. In this paper, we alleviate the need to provide the algorithm with information about task changes by using an online clustering-based approach on a dynamically updated finite pool of samples or gradients. We thereby successfully counteract catastrophic forgetting in one of the hardest settings, namely: domain-incremental learning, a setting for which the problem was previously unsolved. We showcase the benefits of our approach by applying these ideas to projection-based methods, such as A-GEM and OGD, which lead to task-agnostic versions of them. Experiments on real datasets demonstrate the effectiveness of the proposed strategy and its promising performance compared to state-of-the-art methods. Show less
da Silva, C.A.; Hilpert, B.; Bhuvaneshwara, C.; Gebhard, P.; Nunnari, F.; Tsovaltzi, D. 2023
We address the question of why global university rankings should not be used for research evaluation. To answer this question, we analyze four groups of literature (academic vs non-academic... Show moreWe address the question of why global university rankings should not be used for research evaluation. To answer this question, we analyze four groups of literature (academic vs non-academic literature, English-language vs Russian-language literature). The analysis shows that most researchers agree that rankings should not be used to evaluate research. However, they are still used for these purposes directly or indirectly, although recent developments give us hope for a change in the situation in the near future. Show less
Stein. N. van; Winter, R. de; Bäck, T.H.W.; Kononova, A. V. 2023
In this paper, we study human sequential behavior by integrating cognitive, evolutionary, and computational approaches. Our work centers around the emergence of shared vocabularies in the Embodied... Show moreIn this paper, we study human sequential behavior by integrating cognitive, evolutionary, and computational approaches. Our work centers around the emergence of shared vocabularies in the Embodied Communication Game (ECG). Here, participant pairs solve a shared task without access to conventional means of communication, enforcing the emergence of a new communication system. This problem is solved typi- cally by negotiating a shared set of sequential signals that acquire meaning through interactions. Individual differences in Personal Need for Structure (PNS) have been found to influence how this process develops. We trained deep neural networks to mimic the emergence of new communicative systems and used hyperparameter optimization to approximate latent human cognitive variables to explain human behavior. We demonstrate that models based on bidirectional LSTM networks are better at capturing human behavior than unidirectional LSTM networks. This suggests that human sequence processing in the ECG is influenced by expected future states. The approximated variables cannot explain the differences in PNS, but we do provide evidence suggesting that random and uncertainty-directed exploration strategies are combined to develop optimal behavior. Show less
With the continued success of the open RISC-V architecture, practical deployment of RISC-V processors necessitates an in-depth consideration of their testability, safety and security aspects. This... Show moreWith the continued success of the open RISC-V architecture, practical deployment of RISC-V processors necessitates an in-depth consideration of their testability, safety and security aspects. This survey provides an overview of recent developments in this quickly-evolving field. We start with discussing the application of state-of-the-art functional and system-level test solutions to RISC-V processors. Then, we discuss the use of RISC-V processors for safety-related applications; to this end, we outline the essential techniques necessary to obtain safety both in the functional and in the timing domain and review recent processor designs with safety features. Finally, we survey the different aspects of security with respect to RISC-V implementations and discuss the relationship between cryptographic protocols and primitives on the one hand and the RISC-V processor architecture and hardware implementation on the other. We also comment on the role of a RISC-V processor for system security and its resilience against side-channel attacks. Show less
Children are the focal point for studying the link between language and Theory of Mind (ToM) competence. Language and ToM are often studied with younger children and standardized tests, but as both... Show moreChildren are the focal point for studying the link between language and Theory of Mind (ToM) competence. Language and ToM are often studied with younger children and standardized tests, but as both are social competences, data and methods with higher ecological validity are critical.We leverage a corpus of 442 freely-told stories by Dutch children aged 4-12, recorded in their everyday classroom environments, to study language and ToM with NLP-tools. We labelled stories according to the mental depth of story characters children create, as a proxy for their ToM competence ‘in action’, and built a classifier with features encoding linguistic competences identified in existing work as predictive of ToM.We obtain good and fairly robust results (F1-macro = .71), relative to the complexity of the task for humans. Our results are explainable in that we link specific linguistic features such as lexical complexity and sentential complementation, that are relatively independent of children’s ages, to higher levels of character depth. This confirms and extends earlier work, as our study includes older children and socially embedded data from a different domain. Overall, our results support the idea that language and ToM are strongly interlinked, and that in narratives the former can scaffold the latter. Show less
Motivation. Many people interested in learning a programming language choose online courses to develop their skills. The concept of variables is one of the most foundational ones to learn, but can... Show moreMotivation. Many people interested in learning a programming language choose online courses to develop their skills. The concept of variables is one of the most foundational ones to learn, but can be hard to grasp for novices. Variables are researched, but to our knowledge, few empirical observations on how the concept is taught in practice exist. Objective. We investigate how the concept of variables, and the respective naming practices, are taught in introductory Massive Open Online Courses (MOOCs) teaching programming languages. Methods. We gathered qualitative data related to variables and their naming from 17 MOOCs. Collected data include connections to other programming concepts, formal definitions, used analogies, and presented names. Results. We found that variables are often taught in close connection to data types, expressions, and program execution and are often explained using the 'variable as a box' analogy. The latter finding represents a stronger focus on 'storing values', than on naming, memory, and flexibility. Furthermore, MOOCs are inconsistent when teaching naming practices. Conclusions. We recommend teachers and researchers to pay deliberate attention to the definitions and analogies used to explain the concept of variables as well as to naming practices, and in particular to variable name meaning. Show less
This paper explores how students conceptualise the processes involved in human translation (HT) and machine translation (MT), and how they describe the similarities and differences between them.... Show moreThis paper explores how students conceptualise the processes involved in human translation (HT) and machine translation (MT), and how they describe the similarities and differences between them. The paperpresents the results of a survey involving university students (B.A. and M.A.) taking a course on translation who filled out an online questionnaire distributed in Finnish, Dutch and English. Our study finds that students often describe both HT and MT in similar terms, suggesting they do not sufficiently distinguish between them and do not fully understand how MT works. The current study suggests that training in Machine Translation Literacy may need to focus more on the conceptualisations involved and how conceptual and vernacular misconceptions may affect how translators understand human and machine translation. Show less
Valdez, S.; Guerberof-Arenas, A.; Ligtenberg, K. 2023
As part of a larger project on the use of MT in healthcare settings among migrant com- munities, this paper investigates if, when, how, and with what (potential) challenges migrants use MT based on... Show moreAs part of a larger project on the use of MT in healthcare settings among migrant com- munities, this paper investigates if, when, how, and with what (potential) challenges migrants use MT based on a survey of 201 non-native speakers of Dutch currently liv- ing in the Netherlands. Three main findings stand out from our analysis. First, the data shows that most migrants use MT to under- stand health information in Dutch and com- municate with health professionals. How MT is used and received varies depending on the context and the L2 language level, as well as age, but not on the educational level. Sec- ond, some users face challenges of different kinds, including a lack of trust or perceived inaccuracies. Some of these challenges relate to comprehension, bringing us to our third point. We argue that more research is needed to understand the needs of migrants when it comes to translated expert-to-non-expert health communication. This questionnaire helped us identify several topics we hope to explore in the project's next phase. Show less
This paper proposes a new conceptual framework for the creation of an interoperable metaverse seamlessly incorporating AI and blockchain technologies. To achieve this, current issues of... Show moreThis paper proposes a new conceptual framework for the creation of an interoperable metaverse seamlessly incorporating AI and blockchain technologies. To achieve this, current issues of interoperability within the discipline’s state-of-the-art are first identified. Next, a new virtual ontology of the interoperable metaverse is proposed, inspired by recent developments in assemblage theory and in specific concepts by Gilles Deleuze, Manuel DeLanda, and Paulo de Assis. In the third and fourth parts of this paper, a new technical solution is presented: a taxonomy of Periodic Spacetime Sequences, devised for practical implementation of a new distributed version control system. This solution could offer an innovative framework for the interoperable metaverse, which could be built using the proposed taxonomy. Show less