Search

Showing total 3 results
Start Over Topic task analysis Publication Year Range Last 50 years
3 results

1. BEAMES: Interactive Multimodel Steering, Selection, and Inspection for Regression Tasks.

Author

Das, Subhajit, Cashman, Dylan, Chang, Remco, and Endert, Alex

Subjects
*MACHINE learning, *SINGLE people, *VISUAL analytics, *TASKS
Abstract

Interactive model steering helps people incrementally build machine learning models that are tailored to their domain and task. Existing visual analytic tools allow people to steer a single model (e.g., assignment attribute weights used by a dimension reduction model). However, the choice of model is critical in such situations. What if the model chosen is suboptimal for the task, dataset, or question being asked? What if instead of parameterizing and steering this model, a different model provides a better fit? This paper presents a technique to allow users to inspect and steer multiple machine learning models. The technique steers and samples models from a broader set of learning algorithms and model types. We incorporate this technique into a visual analytic prototype, BEAMES, that allows users to perform regression tasks via multimodel steering. This paper demonstrates the effectiveness of BEAMES via a use case, and discusses broader implications for multimodel steering. [ABSTRACT FROM AUTHOR]

Published
2019
Full Text
View/download PDF

2. Incidental learning in a multisensory environment across childhood

Author

Natasha Z. Kirkham, Denis Mareschal, Hayley White, and Hannah Broadbent

Subjects
Paper, Adult, Male, Visual perception, Movement, Cognitive Neuroscience, Stimulus (physiology), 050105 experimental psychology, psyc, Young Adult, 03 medical and health sciences, 0302 clinical medicine, Concept learning, Developmental and Educational Psychology, Humans, Learning, Attention, 0501 psychology and cognitive sciences, Child, 10. No inequality, 4. Education, 05 social sciences, Amodal perception, Age Factors, Attentional control, Incidental learning, Categorization, Papers, Auditory Perception, Visual Perception, Task analysis, Female, Cues, Psychology, Photic Stimulation, 030217 neurology & neurosurgery, Cognitive psychology
Abstract

Multisensory information has been shown to modulate attention in infants and facilitate learning in\ud adults, by enhancing the amodal properties of a stimulus. However, it remains unclear whether this\ud translates to learning in a multisensory environment across middle childhood, and particularly in the\ud case of incidental learning. One hundred and eighty-one children aged between 6 and 10 years\ud participated in this study using a novel Multisensory Attention Learning Task (MALT). Participants\ud were asked to respond to the presence of a target stimulus whilst ignoring distractors. Correct target\ud selection resulted in the movement of the target exemplar to either the upper left or right screen\ud quadrant, according to category membership. Category membership was defined either by visual-only,\ud auditory-only or multisensory information. As early as 6 years of age, children demonstrated greater\ud performance on the incidental categorization task following exposure to multisensory audiovisual\ud cues compared to unisensory information. These findings provide important insight into the use of\ud multisensory information in learning, and particularly on incidental category learning. Implications\ud for the deployment of multisensory learning tasks within education across development will be\ud discussed.

Published
2017

3. Are the literacy difficulties that characterize developmental dyslexia associated with a failure to integrate letters and speech sounds?

Author

Genevieve McArthur, Charles Hulme, Kurt Steinmetzger, Margaret J. Snowling, Debbie Gooch, Yatin Mahajan, and Hannah M. Nash

Subjects
Paper, Adolescent, Cognitive Neuroscience, media_common.quotation_subject, Speech sounds, 050105 experimental psychology, Literacy, letter-sound integration, Dyslexia, 03 medical and health sciences, 0302 clinical medicine, Reaction Time, Developmental and Educational Psychology, medicine, Humans, 0501 psychology and cognitive sciences, Child, Evoked Potentials, Statistical hypothesis testing, media_common, Intelligence quotient, 05 social sciences, medicine.disease, Language acquisition, Acoustic Stimulation, Case-Control Studies, Papers, Speech Perception, Task analysis, Psychology, Priming (psychology), 030217 neurology & neurosurgery, Cognitive psychology
Abstract

The ‘automatic letter‐sound integration hypothesis’ (Blomert, 2011) proposes that dyslexia results from a failure to fully integrate letters and speech sounds into automated audio‐visual objects. We tested this hypothesis in a sample of English‐speaking children with dyslexic difficulties (N = 13) and samples of chronological‐age‐matched (CA; N = 17) and reading‐age‐matched controls (RA; N = 17) aged 7–13 years. Each child took part in two priming experiments in which speech sounds were preceded by congruent visual letters (congruent condition) or Greek letters (baseline). In a behavioural experiment, responses to speech sounds in the two conditions were compared using reaction times. These data revealed faster reaction times in the congruent condition in all three groups. In a second electrophysiological experiment, responses to speech sounds in the two conditions were compared using event‐related potentials (ERPs). These data revealed a significant effect of congruency on (1) the P1 ERP over left frontal electrodes in the CA group and over fronto‐central electrodes in the dyslexic group and (2) the P2 ERP in the dyslexic and RA control groups. These findings suggest that our sample of English‐speaking children with dyslexic difficulties demonstrate a degree of letter‐sound integration that is appropriate for their reading level, which challenges the letter‐sound integration hypothesis.

Published
2016