More Like this

1. A Growth Mindset Message Leads Parents to Choose More Challenging Learning Activities

   https://doi.org/10.3390/jintelligence11100193  

   Tian, Jing ; Bennett-Pierre, Grace ; Tavassolie, Nadia ; Newcombe, Nora S. ; Weinraub, Marsha ; Hindman, Annemarie H. ; Newton, Kristie J. ; Gunderson, Elizabeth A. ( October 2023 , Journal of Intelligence)

   Prior research has shown that the home learning environment (HLE) is critical in the development of spatial skills and that various parental beliefs influence the HLE. However, a comprehensive analysis of the impact of different parental beliefs on the spatial HLE remains lacking, leaving unanswered questions about which specific parental beliefs are most influential and whether inducing a growth mindset can enhance the spatial HLE. To address these gaps, we conducted an online study with parents of 3- to 5-year-olds. We found that parents’ growth mindset about their children’s ability strongly predicted the spatial HLE after controlling for parents’ motivational beliefs about their children, beliefs about their own ability, children’s age, children’s gender, and family SES. Further, reading an article about growth mindset led parents to choose more challenging spatial learning activities for their children. These findings highlight the critical role of parents’ growth mindset in the spatial HLE. Crucially, these findings demonstrate that general growth mindset messages without specific suggestions for parental practices can influence parental behavior intentions. Further, these effects were also observed in the control domain of literacy, underscoring the broad relevance of the growth mindset in the HLE. 

   more » « less
2. The Deep Learning Epilepsy Detection Challenge: Design, Implementation, and Test of a New Crowd-Sourced AI Challenge Ecosystem

   Kiral, Isabell ; Roy, Subhrajit ; Mummert, Todd ; Braz, Alan ; Tsay, Jason ; Tang, Jianbin ; Asif, Umar ; Schaffter, Thomas ; Mehmet, Eren ; Picone, Joseph ; et al ( April 2019 , Challenges in Machine Learning Competitions for All (CiML))

   null (Ed.)

   The DeepLearningEpilepsyDetectionChallenge: design, implementation, andtestofanewcrowd-sourced AIchallengeecosystem Isabell Kiral*, Subhrajit Roy*, Todd Mummert*, Alan Braz*, Jason Tsay, Jianbin Tang, Umar Asif, Thomas Schaffter, Eren Mehmet, The IBM Epilepsy Consortium◊ , Joseph Picone, Iyad Obeid, Bruno De Assis Marques, Stefan Maetschke, Rania Khalaf†, Michal Rosen-Zvi† , Gustavo Stolovitzky† , Mahtab Mirmomeni† , Stefan Harrer† * These authors contributed equally to this work † Corresponding authors: rkhalaf@us.ibm.com, rosen@il.ibm.com, gustavo@us.ibm.com, mahtabm@au1.ibm.com, sharrer@au.ibm.com ◊ Members of the IBM Epilepsy Consortium are listed in the Acknowledgements section J. Picone and I. Obeid are with Temple University, USA. T. Schaffter is with Sage Bionetworks, USA. E. Mehmet is with the University of Illinois at Urbana-Champaign, USA. All other authors are with IBM Research in USA, Israel and Australia. Introduction This decade has seen an ever-growing number of scientific fields benefitting from the advances in machine learning technology and tooling. More recently, this trend reached the medical domain, with applications reaching from cancer diagnosis [1] to the development of brain-machine-interfaces [2]. While Kaggle has pioneered the crowd-sourcing of machine learning challenges to incentivise data scientists from around the world to advance algorithm and model design, the increasing complexity of problem statements demands of participants to be expert data scientists, deeply knowledgeable in at least one other scientific domain, and competent software engineers with access to large compute resources. People who match this description are few and far between, unfortunately leading to a shrinking pool of possible participants and a loss of experts dedicating their time to solving important problems. Participation is even further restricted in the context of any challenge run on confidential use cases or with sensitive data. Recently, we designed and ran a deep learning challenge to crowd-source the development of an automated labelling system for brain recordings, aiming to advance epilepsy research. A focus of this challenge, run internally in IBM, was the development of a platform that lowers the barrier of entry and therefore mitigates the risk of excluding interested parties from participating. The challenge: enabling wide participation With the goal to run a challenge that mobilises the largest possible pool of participants from IBM (global), we designed a use case around previous work in epileptic seizure prediction [3]. In this “Deep Learning Epilepsy Detection Challenge”, participants were asked to develop an automatic labelling system to reduce the time a clinician would need to diagnose patients with epilepsy. Labelled training and blind validation data for the challenge were generously provided by Temple University Hospital (TUH) [4]. TUH also devised a novel scoring metric for the detection of seizures that was used as basis for algorithm evaluation [5]. In order to provide an experience with a low barrier of entry, we designed a generalisable challenge platform under the following principles: 1. No participant should need to have in-depth knowledge of the specific domain. (i.e. no participant should need to be a neuroscientist or epileptologist.) 2. No participant should need to be an expert data scientist. 3. No participant should need more than basic programming knowledge. (i.e. no participant should need to learn how to process fringe data formats and stream data efficiently.) 4. No participant should need to provide their own computing resources. In addition to the above, our platform should further • guide participants through the entire process from sign-up to model submission, • facilitate collaboration, and • provide instant feedback to the participants through data visualisation and intermediate online leaderboards. The platform The architecture of the platform that was designed and developed is shown in Figure 1. The entire system consists of a number of interacting components. (1) A web portal serves as the entry point to challenge participation, providing challenge information, such as timelines and challenge rules, and scientific background. The portal also facilitated the formation of teams and provided participants with an intermediate leaderboard of submitted results and a final leaderboard at the end of the challenge. (2) IBM Watson Studio [6] is the umbrella term for a number of services offered by IBM. Upon creation of a user account through the web portal, an IBM Watson Studio account was automatically created for each participant that allowed users access to IBM's Data Science Experience (DSX), the analytics engine Watson Machine Learning (WML), and IBM's Cloud Object Storage (COS) [7], all of which will be described in more detail in further sections. (3) The user interface and starter kit were hosted on IBM's Data Science Experience platform (DSX) and formed the main component for designing and testing models during the challenge. DSX allows for real-time collaboration on shared notebooks between team members. A starter kit in the form of a Python notebook, supporting the popular deep learning libraries TensorFLow [8] and PyTorch [9], was provided to all teams to guide them through the challenge process. Upon instantiation, the starter kit loaded necessary python libraries and custom functions for the invisible integration with COS and WML. In dedicated spots in the notebook, participants could write custom pre-processing code, machine learning models, and post-processing algorithms. The starter kit provided instant feedback about participants' custom routines through data visualisations. Using the notebook only, teams were able to run the code on WML, making use of a compute cluster of IBM's resources. The starter kit also enabled submission of the final code to a data storage to which only the challenge team had access. (4) Watson Machine Learning provided access to shared compute resources (GPUs). Code was bundled up automatically in the starter kit and deployed to and run on WML. WML in turn had access to shared storage from which it requested recorded data and to which it stored the participant's code and trained models. (5) IBM's Cloud Object Storage held the data for this challenge. Using the starter kit, participants could investigate their results as well as data samples in order to better design custom algorithms. (6) Utility Functions were loaded into the starter kit at instantiation. This set of functions included code to pre-process data into a more common format, to optimise streaming through the use of the NutsFlow and NutsML libraries [10], and to provide seamless access to the all IBM services used. Not captured in the diagram is the final code evaluation, which was conducted in an automated way as soon as code was submitted though the starter kit, minimising the burden on the challenge organising team. Figure 1: High-level architecture of the challenge platform Measuring success The competitive phase of the "Deep Learning Epilepsy Detection Challenge" ran for 6 months. Twenty-five teams, with a total number of 87 scientists and software engineers from 14 global locations participated. All participants made use of the starter kit we provided and ran algorithms on IBM's infrastructure WML. Seven teams persisted until the end of the challenge and submitted final solutions. The best performing solutions reached seizure detection performances which allow to reduce hundred-fold the time eliptologists need to annotate continuous EEG recordings. Thus, we expect the developed algorithms to aid in the diagnosis of epilepsy by significantly shortening manual labelling time. Detailed results are currently in preparation for publication. Equally important to solving the scientific challenge, however, was to understand whether we managed to encourage participation from non-expert data scientists. Figure 2: Primary occupation as reported by challenge participants Out of the 40 participants for whom we have occupational information, 23 reported Data Science or AI as their main job description, 11 reported being a Software Engineer, and 2 people had expertise in Neuroscience. Figure 2 shows that participants had a variety of specialisations, including some that are in no way related to data science, software engineering, or neuroscience. No participant had deep knowledge and experience in data science, software engineering and neuroscience. Conclusion Given the growing complexity of data science problems and increasing dataset sizes, in order to solve these problems, it is imperative to enable collaboration between people with differences in expertise with a focus on inclusiveness and having a low barrier of entry. We designed, implemented, and tested a challenge platform to address exactly this. Using our platform, we ran a deep-learning challenge for epileptic seizure detection. 87 IBM employees from several business units including but not limited to IBM Research with a variety of skills, including sales and design, participated in this highly technical challenge. 

   more » « less
3. Children's engineering identities‐in‐practice : An exploration of child–adult interactions in an out‐of‐school context

   https://doi.org/10.1002/jee.20553  

   Simpson, Amber ; Knox, Peter N. ; Yang, Jing ( August 2023 , Journal of Engineering Education)

   Research points to family talk and interactions involving STEM concepts as one of the most influential informal learning experiences that shape an individual's STEM identity development and encourage their pursuit of a STEM career. However, a recent literature review uncovers limited research regarding the development of engineering identity in young children.

   The purpose of this study was to add to this scant literature by exploring how children position themselves as engineers and how children are positioned as engineers through interactions with parents and other adults within a program focused on family engagement within an engineering design process.

   This study includes two parent–child dyads. We collected and analyzed approximately 19.5 h of video data of the two child–parent dyads interacting with one another throughout an engineering design process as part of an out‐of‐school program.

   Results highlight three ways in which the two children enacted various engineering identities through their positioning, negotiation, and acceptance and/or rejection of positionalities as they engaged in an engineering design process with a parent. These identity enactments included (a) possessing knowledge and authority to make decisions regarding the development of their self‐identified engineering problem and prototype; (b) questioning and challenging adult ideas, solutions, and construction of prototypes; and (c) documenting and communicating their thinking regarding the engineering design through sketches and notes.

   The significance of this study lies in its potential to change the landscape of those who pursue an engineering career and to contribute to the limited research and ongoing conversations about how to foster environments that support families in creative and collaborative learning specific to the engineering discipline.

    

   more » « less
4. The Influence of Connecting Funds of Knowledge to Beliefs about Performance, Classroom Belonging, and Graduation Certainty for First-Generation College Students

   https://doi.org/10.18260/1-2--35343  

   Verdín, Dina ; Smith, Jessica ; Lucena, Juan. ( January 2020 , American Society for Engineering Education)

   First-generation college students in engineering accumulate bodies of knowledge through their working-class families. In our ethnographic data of first-generation college students, we identified tinkering knowledge from home and from work, perspective taking, mediational ability, and connecting experiences as knowledge sources brought to engineering. The purpose of this paper was to understand how first-generation college students’ accumulated bodies of knowledge (i.e., funds of knowledge) support their beliefs about performing well in engineering coursework, feeling a sense of belonging in the classroom, and certainty of graduating. Data for this study came from a survey administered in the Fall of 2018 from ten universities across the US. In this study, only the sample of students who indicated their parents had less than a bachelor’s degree (n = 378) were used. A structural equation modeling technique was employed to examine several interconnected research questions pertaining to funds of knowledge, performance/competence beliefs, classroom belongingness, and certainty of graduating with an engineering degree. Our analysis demonstrates that the accumulated bodies of knowledge obtained through tinkering at home, tinkering at work, and the skill of being a mediator served to scaffold concepts that students were currently learning in engineering. There was a negative direct relationship between students’ ability to make connections between their home activities to scaffold what they are currently learning and their certainty of graduating with an engineering degree. However, first-generation college students’ perceptions of performing well in their engineering coursework and their sense of belonging in the classroom positively supported their certainty of graduating thus emphasizing the importance of connecting students’ funds of knowledge to engineering coursework and classroom instruction. Implications for possible approaches towards connecting first-generation college students’ funds of knowledge to engineering coursework and classroom culture are discussed. 

   more » « less
5. Attention to the integration of literacy: A systematic review of early math interventions in informal learning environments

   https://doi.org/10.1002/pits.23150  

   Carter, Hannah ; Nelson, Gena ; Boedeker, Peter ; Buckmiller, Claire Werlin ; Eames, Jessie ; Knowles, Emma ( January 2024 , Psychology in the Schools)

   Links between the development of early literacy and math skills are well documented. This systematic review focuses on how literacy is incorporated into informal math intervention studies for children in preschool to third grade, which has implications for researchers and those training caregivers to support their children at home. We reviewed 51 experimental or quasi‐experimental studies published from 1981 to 2021 that investigated the effectiveness of math interventions in informal learning environments with a caregiver interventionist. Findings revealed that 100% of studies included literacy in some way. We also investigated what types of literacy activities were integrated, how literacy was a part of data sources collected, and in what ways literacy was mentioned explicitly by authors in research reports. The most common literacy activity was speaking and listening, and the most frequently included literacy data source was standardized literacy achievement measures. Finally, researchers in the included studies did not detail literacy throughout their research reports. While early math interventions often integrate literacy, the research base including math interventions would benefit from more explicit rationales for their use of literacy, and caregivers should be provided information to help understand how literacy should be a part of the way they work with their child on math at home.

    

   more » « less