Computational brain & behavior最新文献_第10页

Alleviating the Cold Start Problem in Adaptive Learning using Data-Driven Difficulty Estimates 用数据驱动的难度估计缓解自适应学习中的冷启动问题

Computational brain & behavior Pub Date : 2020-06-30 DOI: 10.31234/osf.io/hf2vw

Maarten van der Velde, Florian Sense, J. Borst, H. van Rijn

{"title":"Alleviating the Cold Start Problem in Adaptive Learning using Data-Driven Difficulty Estimates","authors":"Maarten van der Velde, Florian Sense, J. Borst, H. van Rijn","doi":"10.31234/osf.io/hf2vw","DOIUrl":"https://doi.org/10.31234/osf.io/hf2vw","url":null,"abstract":"An adaptive learning system offers a digital learning environment that adjusts itself to the individual learner and learning material. By refining its internal model of the learner and material over time, such a system continually improves its ability to present appropriate exercises that maximise learning gains. In many cases, there is an initial mismatch between the internal model and the learner’s actual performance on the presented items, causing a “cold start” during which the system is poorly adjusted to the situation. In this study, we implemented several strategies for mitigating this cold start problem in an adaptive fact learning system and experimentally tested their effect on learning performance. The strategies included predicting difficulty for individual learner-fact pairs, individual learners, individual facts, and the set of facts as a whole. We found that cold start mitigation improved learning outcomes, provided that there was sufficient variability in the difficulty of the study material. Informed individualised predictions allowed the system to schedule learners’ study time more effectively, leading to an increase in response accuracy during the learning session as well as improved retention of the studied items afterwards. Our findings show that addressing the cold start problem in adaptive learning systems can have a real impact on learning outcomes. We expect this to be particularly valuable in real-world educational settings with large individual differences between learners and highly diverse materials.","PeriodicalId":72660,"journal":{"name":"Computational brain & behavior","volume":"10 1","pages":"231-249"},"PeriodicalIF":0.0,"publicationDate":"2020-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91147069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

Modeling Optimal Stopping in Changing Environments: a Case Study in Mate Selection 在变化的环境中建模最优停止:配偶选择的案例研究

Computational brain & behavior Pub Date : 2020-06-26 DOI: 10.1007/s42113-020-00085-9

M. Lee, Karyssa A. Courey

引用次数: 6

Modeling Retest Effects in a Longitudinal Measurement Burst Study of Memory. 记忆纵向测量突发研究中的模型重测效应。

Computational brain & behavior Pub Date : 2020-06-01 Epub Date: 2019-08-14 DOI: 10.1007/s42113-019-00047-w

Adam W Broitman, Michael J Kahana, M Karl Healey

{"title":"Modeling Retest Effects in a Longitudinal Measurement Burst Study of Memory.","authors":"Adam W Broitman, Michael J Kahana, M Karl Healey","doi":"10.1007/s42113-019-00047-w","DOIUrl":"https://doi.org/10.1007/s42113-019-00047-w","url":null,"abstract":"Longitudinal designs must deal with the confound between increasing age and increasing task experience (i.e., retest effects). Most existing methods for disentangling these factors rely on large sample sizes and are impractical for smaller scale projects. Here, we show that a measurement burst design combined with a model of retest effects can be used to study age-related change with modest sample sizes. A combined model of age-related change and retest-related effects was developed. In a simulation experiment, we show that with sample sizes as small as n = 8, the model can reliably detect age effects of the size reported in the longitudinal literature while avoiding false positives when there is no age effect. We applied the model to data from a measurement burst study in which eight subjects completed a burst of seven sessions of free recall every year for five years. Six additional subjects completed a burst only in years 1 and 5. They should, therefore, have smaller retest effects but equal age effects. The raw data suggested slight improvement in memory over five years. However, applying the model to the yearly-testing group revealed that a substantial positive retest effect was obscuring stability in memory performance. Supporting this finding, the control group showed a smaller retest effect but an equal age effect. Measurement burst designs combined with models of retest effects allow researchers to employ longitudinal designs in areas where previously only cross-sectional designs were feasible.","PeriodicalId":72660,"journal":{"name":"Computational brain & behavior","volume":"3 2","pages":"200-207"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1007/s42113-019-00047-w","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38680054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Neural habituation enhances novelty detection: an EEG study of rapidly presented words. 神经习惯化可增强新奇感检测：快速呈现单词的脑电图研究。

Computational brain & behavior Pub Date : 2020-06-01 Epub Date: 2019-12-18 DOI: 10.1007/s42113-019-00071-w

Len P L Jacob, David E Huber

{"title":"Neural habituation enhances novelty detection: an EEG study of rapidly presented words.","authors":"Len P L Jacob, David E Huber","doi":"10.1007/s42113-019-00071-w","DOIUrl":"10.1007/s42113-019-00071-w","url":null,"abstract":"Huber and O'Reilly (2003) proposed that neural habituation aids perceptual processing, separating neural responses to currently viewed objects from recently viewed objects. However, synaptic depression has costs, producing repetition deficits. Prior work confirmed the transition from repetition benefits to deficits with increasing duration of a prime object, but the prediction of enhanced novelty detection was not tested. The current study examined this prediction with a same/different word priming task, using support vector machine (SVM) classification of EEG data, ERP analyses focused on the N400, and dynamic neural network simulations fit to behavioral data to provide a priori predictions of the ERP effects. Subjects made same/different judgements to a response word in relation to an immediately preceding brief target word; prime durations were short (50ms) or long (400ms), and long durations decreased P100/N170 responses to the target word, suggesting that this manipulation increased habituation. Following long duration primes, correct \"different\" judgments of primed response words increased, evidencing enhanced novelty detection. An SVM classifier predicted trial-by-trial behavior with 66.34% accuracy on held-out data, with greatest predictive power at a time pattern consistent with the N400. The habituation model was augmented with a maintained semantics layer (i.e., working memory) to generate behavior and N400 predictions. A second experiment used response-locked ERPs, confirming the model's assumption that residual activation in working memory is the basis of novelty decisions. These results support the theory that neural habituation enhances novelty detection, and the model assumption that the N400 reflects updating of semantic information in working memory.","PeriodicalId":72660,"journal":{"name":"Computational brain & behavior","volume":"3 2","pages":"208-227"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7447193/pdf/nihms-1546975.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38414587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Explanation or Modeling: a Reply to Kellen and Klauer 解释还是建模:对Kellen和Klauer的回复

Computational brain & behavior Pub Date : 2020-04-15 DOI: 10.1007/s42113-020-00077-9

Marco Ragni, P. Johnson-Laird

引用次数: 2

Beyond Rescorla–Wagner: the Ups and Downs of Learning 超越Rescorla-Wagner:学习的起起落落

Computational brain & behavior Pub Date : 2020-04-10 DOI: 10.1007/s42113-021-00103-4

G. Calcagni, Justin A. Harris, R. Pellón

引用次数: 1

Real-time Adaptive Design Optimization Within Functional MRI Experiments 功能MRI实验中的实时自适应设计优化

Computational brain & behavior Pub Date : 2020-04-02 DOI: 10.1007/s42113-020-00079-7

Giwon Bahg, P. Sederberg, Jay I. Myung, Xiangrui Li, M. Pitt, Zhong-Lin Lu, Brandon M. Turner

引用次数: 3

Modeling the Wason Selection Task: a Response to Ragni and Johnson-Laird (2020) 建模沃森选择任务:对Ragni和Johnson-Laird(2020)的回应

Computational brain & behavior Pub Date : 2020-04-01 DOI: 10.1007/s42113-020-00086-8

David Kellen, K. C. Klauer

引用次数: 1

A Cautionary Note on Evidence-Accumulation Models of Response Inhibition in the Stop-Signal Paradigm 关于停止-信号范式中反应抑制的证据积累模型的警告

Computational brain & behavior Pub Date : 2020-03-30 DOI: 10.1007/s42113-020-00075-x

D. Matzke, G. Logan, A. Heathcote

引用次数: 12

Modeling Preference Reversals in Context Effects over Time 随着时间的推移，环境影响下偏好逆转的建模

Computational brain & behavior Pub Date : 2020-03-27 DOI: 10.1007/s42113-020-00078-8

Andrea M. Cataldo, A. Cohen

引用次数: 9