We present our design and implementation of Standoff, an innovative benchmark suite of computational theory of mind tasks, based on the competitive feeding paradigm from comparative psychology. We find that a small co...
详细信息
ISBN:
(纸本)9798350348569;9798350348552
We present our design and implementation of Standoff, an innovative benchmark suite of computational theory of mind tasks, based on the competitive feeding paradigm from comparative psychology. We find that a small convolutional LSTM model without explicit theory of mind mechanisms can reach high levels of accuracy when exposed to the full variety of our task design during training. Such a model faces generalization challenges when exposed to narrower subsets of tasks. Finally, we discuss how this test may be used as a gateway for studying theory of mind skills beyond attribution of seeing and knowing.
Color constancy (CC) describes the ability of the visual system to perceive an object as having a relatively constant color despite changes in lighting conditions. While CC and its limitations have been carefully char...
详细信息
ISBN:
(纸本)9798350348569;9798350348552
Color constancy (CC) describes the ability of the visual system to perceive an object as having a relatively constant color despite changes in lighting conditions. While CC and its limitations have been carefully characterized in humans, it is still unclear how the visual system acquires this ability during development. Here, we present a first study showing that CC develops in a neural network trained in a self-supervised manner through an invariance learning objective. During learning, objects are presented under changing illuminations, while the network aims to map subsequent views of the same object onto close-by latent representations. This gives rise to representations that are largely invariant to the illumination conditions, offering a plausible example of how CC could emerge during human cognitive development via a form of self-supervised learning.
The proceedings contain 18 papers. The topics discussed include: all quiet on the Covid-19 front! - real experience must be bought for power electronics beginners;simulation and design of control systems: a rapid soft...
ISBN:
(纸本)9781665489904
The proceedings contain 18 papers. The topics discussed include: all quiet on the Covid-19 front! - real experience must be bought for power electronics beginners;simulation and design of control systems: a rapid software prototyping class for mechanical engineering students;diploma projects for lab equipment rental - how students can help university in the Covid-19 era;solution-oriented teaching method of electric power circuit design for online on-demand video streaming lecture course;differences in visibility of students' proficiency by grading methods in energy electronics-related lectures based on DX format;proposal of a DX method for lathe operation practical training with respect to motivation and an operative sense of agency;integrating different modelling formalisms supporting co-design development of controllers for cyber-physical systems — a case study;and an education seminar utilizing both experiments and e-learning for beginners in the power electronics field.
Humans can acquire language by segmenting continuous speech signals with a double articulation structure into phonemes and words without explicit boundary points or labels, and learn the transition rules of words as g...
详细信息
ISBN:
(纸本)9798350348569;9798350348552
Humans can acquire language by segmenting continuous speech signals with a double articulation structure into phonemes and words without explicit boundary points or labels, and learn the transition rules of words as grammar. learning the double articulation structure of speech signals is crucial for realizing robots with similar language learning abilities to those of humans. In this study, we propose a novel probabilistic generative model (PGM) that can learn phonemes, words, and grammar from continuous speech signals by hierarchically connecting the Gaussian process hidden semi-Markov model and hidden semiMarkov model (HSMM). In the proposed method, the parameters of each PGM are updated mutually and the grammatical structures affect the phonemes and words, thereby enabling the accurate learning of phonemes and words. The experimental results reveal that the proposed approach, including grammar learning, can segment continuous speech into phonemes and words more accurately than conventional methods. Furthermore, we found that grammar learning significantly affected the accurate estimation of the number of words in the sentence.
This paper surveys the latest unsupervised anomaly detection methodologies applied to health insurance fraud, covering studies from 2017 to 2024. Our review includes a variety of machine-learning approaches, evaluatin...
详细信息
ISBN:
(纸本)9798350366396;9798350366389
This paper surveys the latest unsupervised anomaly detection methodologies applied to health insurance fraud, covering studies from 2017 to 2024. Our review includes a variety of machine-learning approaches, evaluating their effectiveness in handling complex, high-dimensional, and imbalanced healthcare datasets. Techniques such as Isolation Forest, Bayesian hierarchical models, and deep autoencoders demonstrate superior performance compared to traditional methods. Despite significant advancements, gaps remain with regard to transfer learning, interpretability and explainability of models, and the development of real-time, incremental learning algorithms. Future research should focus on these areas to enhance fraud detection accuracy and trust. Our work aims to provide a valuable resource for researchers and practitioners, supporting the development of more robust and adaptive fraud detection systems to protect healthcare integrity and reduce financial losses.
In collaborative software development, bots have become increasingly prevalent, making effective bot recommendation a key factor in enhancing development efficiency. This study aims to explore the application and effi...
详细信息
ISBN:
(纸本)9798350376975;9798350376968
In collaborative software development, bots have become increasingly prevalent, making effective bot recommendation a key factor in enhancing development efficiency. This study aims to explore the application and efficacy of deep learning models in bot recommendation. Focusing on the Code-BERT model, we conduct a comprehensive evaluation through comparison with baseline models, parameter tuning (including batch size and learning rate), and the incorporation of language data. Our findings demonstrate that under specific conditions, the CodeBERT model exhibits superior performance in bot recommendation tasks, with parameter adjustments and the inclusion of language data significantly impacting the model's effectiveness. These insights offer new perspectives and strategies for the effective recommendation of bots in open-source software platforms.
Online education platforms demand that reliable and measurable assessment and feedback generation systems be developed to ensure quality. In particular, classes requiring large software development projects need step-...
详细信息
ISBN:
(纸本)9798350300543
Online education platforms demand that reliable and measurable assessment and feedback generation systems be developed to ensure quality. In particular, classes requiring large software development projects need step-wise requirement specifications, verification and validation to affect proper assessment in phases. Such monitoring and assessment support is virtually non-existent in contemporary tutoring or learning management systems. In this paper, we propose a novel implementation of a team-based project management and assessment system for online database classes as an integral and vital component of a modern learning management system.
Machine learning (ML) is widely used in healthcare applications to diagnose diseases, forecast disease progression, develop personalized treatment plans, and aid in drug discovery and development [1]. The development ...
详细信息
Teaching Chinese characters is an essential component of language education in Chinese primary schools. However, students frequently encounter difficulties with incorrectly written characters. Current educational meth...
详细信息
ISBN:
(纸本)9798331540869;9798331540852
Teaching Chinese characters is an essential component of language education in Chinese primary schools. However, students frequently encounter difficulties with incorrectly written characters. Current educational methods often fail to offer timely and specific learning resources to address these challenges. This paper introduces a novel learning tool tailored for primary school students to tackle the issue of error-prone Chinese characters. The tool leverages sophisticated handwriting recognition and Chinese spell-check technologies as its fundamental development features. A quasi-experimental study indicated that the group utilizing the experimental tool consistently surpassed the control group in both interim and final assessments, corroborating the efficacy of the tool. Students valued the tool for its promptness, pertinence, and targeted learning content. Potential future enhancements may encompass diversifying the available resources, refining personalized recommendations based on individual learner profiles, and more seamlessly integrating the tool with conventional teaching approaches to further augment learning outcomes for error-prone Chinese characters.
Imitation can allow us to quickly gain an understanding of a new task. Through a demonstration, we can gain direct knowledge about which actions need to be performed and which goals they have. In this paper, we introd...
详细信息
ISBN:
(纸本)9798350348569;9798350348552
Imitation can allow us to quickly gain an understanding of a new task. Through a demonstration, we can gain direct knowledge about which actions need to be performed and which goals they have. In this paper, we introduce a new approach to imitation learning that tackles the challenges of a robot imitating a human, such as the change in perspective and body schema. Our approach can use a single human demonstration to abstract information about the demonstrated task, and use that information to generalise and replicate it. We facilitate this ability by a new integration of two state-of-the-art methods: a diffusion action segmentation model to abstract temporal information from the demonstration and an open vocabulary object detector for spatial information. Furthermore, we refine the abstracted information and use symbolic reasoning to create an action plan utilising inverse kinematics, to allow the robot to imitate the demonstrated action.
暂无评论