An official website of the United States government
Data leakage remains a pervasive issue in machine learning (ML), especially when applied to science, leading to overly optimistic performance estimates and irreproducible findings. Despite its prevalence, data leakage receives limited attention in ML education, in part due to the lack of accessible, hands-on teaching resources. To address this gap, we developed interactive learning modules in which students reproduce examples from academic publications that are affected by data leakage, then repeat the evaluation without the data leakage error to see how the finding is affected. These modules were deployed by the authors in two introductory machine learning courses, enabling students to explore common forms of leakage and their impact on model reliability. Following their engagement with these materials, student feedback highlighted increased awareness of subtle pitfalls that can compromise machine learning workflows.
more »
« less
This content will become publicly available on February 12, 2026
PhysioML: A Web-Based Tool for Machine Learning Education with Real-Time Physiological Data
Artificial Intelligence and Machine Learning continue to increase in popularity. As a result, several new approaches to machine learning education have emerged in recent years. Many existing interactive techniques utilize text, image, and video data to engage students with machine learning. However, the use of physiological sensors for machine learning education activities is significantly unexplored. This paper presents findings from a study exploring students’ experiences learning basic machine learning concepts while using physiological sensors to control an interactive game. In particular, the sensors measured electrical activity generated from students’ arm muscles. Activities featuring physiological sensors produced similar outcomes when compared to exercises that leveraged image data. While students’ machine learning self-efficacy increased in both conditions, students seemed more curious about machine learning after working with the physiological sensor. These results suggest that PhysioML may provide learning support similar to traditional ML education approaches while engaging students with novel interactive physiological sensors. We discuss these findings and reflect on ways physiological sensors may be used to augment traditional data types during classroom activities focused on machine learning.
more »
« less
- Award ID(s):
- 2045561
- PAR ID:
- 10585693
- Publisher / Repository:
- ACM
- Date Published:
- ISBN:
- 9798400705311
- Page Range / eLocation ID:
- 485 to 491
- Format(s):
- Medium: X
- Location:
- Pittsburgh PA USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Existing approaches to teaching artificial intelligence and machine learning often focus on the use of pre-trained models or fine-tuning an existing black-box architecture. We believe advanced ML topics, such as optimization and adversarial examples, can be learned by early high school age students given appropriate support. Our approach focuses on enabling students to develop deep intuition about these complex concepts by first making them accessible to novices through interactive tools, pre-programmed games, and carefully designed programming activities. Then, students are able to engage with the concepts via meaningful, hands-on experiences that span the entire ML process from data collection to model optimization and inspection.more » « less
-
It is believed that if students are well engaged in the learning process within the classroom, they will continue the learning process independently outside the classroom. To facilitate such out-of-class learning, there is a plethora of traditional techniques with a variety of learning theoretical backgrounds. While out-of-class activities based on these techniques have shown to improve a student’s overall quality of learning, traditional activities lack the supervision, instant feedback, and personalization that the current generation of students expects. With the rising cost of college tuition, many of today’s students are working more hours outside of an educational setting and therefore need more supervision and encouragement than their predecessors. These factors make traditional out-of-class activities not effective to achieve the desired level of student learning and engagement outside the classroom. The faculty needs to rethink ways to redesign traditional out-of-class activities to make these activities more effective for this generation of students. This paper presents a review of the literature on and categorization of traditional out-of-class activities. The paper also discusses the results of a survey of what the faculty is doing to engage and continue student learning outside the classroom. Finally, the paper presents a new way of designing and delivering out-of-class activities that have the potential to increase student engagement with the help of instructional scaffolding, interactive activities, and personalization and adaptation.more » « less
-
Existing approaches to teaching artifcial intelligence and machine learning (ML) often focus on the use of pre-trained models or fne-tuning an existing black-box architecture. We believe ML techniques and core ML topics, such as optimization and adversarial examples, can be designed for high school age students given appropriate support. Our curricular approach focuses on teaching ML ideas by enabling students to develop deep intuition about these complex concepts by first making them accessible to novices through interactive tools, pre-programmed games, and carefully designed programming activities. Then, students are able to engage with the concepts via meaningful, hands-on experiences that span the entire ML process from data collection to model optimization and inspection. This paper describes our AI & Cybersecurity for Teens suite of curricular activities aimed at high school students and teachers.more » « less
-
null (Ed.)Applications of generative models such as Generative Adversarial Networks (GANs) have made their way to social media platforms that children frequently interact with. While GANs are associated with ethical implications pertaining to children, such as the generation of Deepfakes, there are negligible efforts to educate middle school children about generative AI. In this work, we present a generative models learning trajectory (LT), educational materials, and interactive activities for young learners with a focus on GANs, creation and application of machine-generated media, and its ethical implications. The activities were deployed in four online workshops with 72 students (grades 5-9). We found that these materials enabled children to gain an understanding of what generative models are, their technical components and potential applications, and benefits and harms, while reflecting on their ethical implications. Learning from our findings, we propose an improved learning trajectory for complex socio-technical systems.more » « less
