More Like this

1. Conducting the Pilot Study of Integrating AI: An Experience Integrating Machine Learning into Upper Elementary Robotics Learning (Work in Progress)

   Xu, G.; Zabner, D.; Cross, J.; Nadler, D.; Coxon, S.; Engelkenjohn, K. (June 2023, ASEE annual conference exposition proceedings)

   Artificial Intelligence (AI) enhanced systems are widely adopted in post-secondary education, however, tools and activities have only recently become accessible for teaching AI and machine learning (ML) concepts to K-12 students. Research on K-12 AI education has largely included student attitudes toward AI careers, AI ethics, and student use of various existing AI agents such as voice assistants; most of which has focused on high school and middle school. There is no consensus on which AI and Machine Learning concepts are grade-appropriate for elementary-aged students or how elementary students explore and make sense of AI and ML tools. AI is a rapidly evolving technology and as future decision-makers, children will need to be AI literate[1]. In this paper, we will present elementary students’ sense-making of simple machine-learning concepts. Through this project, we hope to generate a new model for introducing AI concepts to elementary students into school curricula and provide tangible, trainable representations of ML for students to explore in the physical world. In our first year, our focus has been on simpler machine learning algorithms. Our desire is to empower students to not only use AI tools but also to understand how they operate. We believe that appropriate activities can help late elementary-aged students develop foundational AI knowledge namely (1) how a robot senses the world, and (2) how a robot represents data for making decisions. Educational robotics programs have been repeatedly shown to result in positive learning impacts and increased interest[2]. In this pilot study, we leveraged the LEGO® Education SPIKE™ Prime for introducing ML concepts to upper elementary students. Through pilot testing in three one-week summer programs, we iteratively developed a limited display interface for supervised learning using the nearest neighbor algorithm. We collected videos to perform a qualitative evaluation. Based on analyzing student behavior and the process of students trained in robotics, we found some students show interest in exploring pre-trained ML models and training new models while building personally relevant robotic creations and developing solutions to engineering tasks. While students were interested in using the ML tools for complex tasks, they seemed to prefer to use block programming or manual motor controls where they felt it was practical. 

   more » « less
2. Model, Data and Reward Repair: Trusted Machine Learning for Markov Decision Processes

   https://doi.org/10.1109/DSN-W.2018.00064  

   Ghosh, Shalini; Jha, Susmit; Tiwari, Ashish; Lincoln, Patrick; Zhu, Xiaojin (January 2018, 48th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W))

   When machine learning (ML) algorithms are used in mission-critical domains (e.g., self-driving cars, cyber security) or life-critical domains (e.g., surgical robotics), it is often important to ensure that the learned models satisfy some high-level correctness requirements — these requirements can be instantiated in particular domains via constraints like safety (e.g., a robot arm should not come within five meters of any human operator during any phase of performing an autonomous operation) or liveness (e.g., a car should eventually cross a 4-way intersection). Such constraints can be formally described in propositional logic, first order logic or temporal logics such as Probabilistic Computation Tree Logic (PCTL)[31]. For example, in a lane change controller we can enforce the following PCTL safety property on seeing a slow-moving truck in front: Pr>0.99[F(changedLane or reducedSpeed)] , where F is the eventually operator in PCTL logic — this property states that the car should eventually change lanes or reduce speed with high probability (greater than 0.99). Trusted Machine Learning (TML) refers to a learning methodology that ensures that the specified properties are satisfied. 

   more » « less
3. Creating an authoring tool for K-12 teachers to design ML-supported scientific inquiry learning

   https://doi.org/10.1145/3613905.3650762  

   Zhou, Xiaofei; Tang, Jingwan; Lyu, Hanjia; Liu, Xinyi; Zhang, Zhenhao; Qin, Lichen; Au, Fiona; Sarkar, Advait; Bai, Zhen (May 2024, ACM)

   Despite significant advances in machine learning (ML) applications within science, there is a notable gap in its integration into K-12 education to enhance data literacy and scientific inquiry (SI) skills. To address this gap, we enable K-12 teachers with limited technical expertise to apply ML for pattern discovery and explore how ML can empower educators in teaching SI. We design a web-based tool, ML4SI, for teachers to create ML-supported SI learning activities. This tool can also facilitate collecting data about the interaction between ML techniques and SI learning. A pilot study with three K-12 teachers provides insights to prepare the next generation for the era of big data through ML-supported SI learning. 

   more » « less
4. Swift machine learning model serving scheduling: a region based reinforcement learning approach

   https://doi.org/10.1145/3295500.3356164  

   Qin, Heyang; Zawad, Syed; Zhou, Yanqi; Yang, Lei; Zhao, Dongfang; Yan, Feng (November 2019, Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC'19))

   The success of machine learning has prospered Machine-Learning-as-a-Service (MLaaS) - deploying trained machine learning (ML) models in cloud to provide low latency inference services at scale. To meet latency Service-Level-Objective (SLO), judicious parallelization at both request and operation levels is utterly important. However, existing ML systems (e.g., Tensorflow) and cloud ML serving platforms (e.g., SageMaker) are SLO-agnostic and rely on users to manually configure the parallelism. To provide low latency ML serving, this paper proposes a swift machine learning serving scheduling framework with a novel Region-based Reinforcement Learning (RRL) approach. RRL can efficiently identify the optimal parallelism configuration under different workloads by estimating performance of similar configurations with that of the known ones. We both theoretically and experimentally show that the RRL approach can outperform state-of-the-art approaches by finding near optimal solutions over 8 times faster while reducing inference latency up to 79.0% and reducing SLO violation up to 49.9%. 

   more » « less
5. Strengthening Children’s Privacy Literacy through Contextual Integrity

   https://doi.org/10.17645/mac.v8i4.3236  

   Kumar, Priya C.; Subramaniam, Mega; Vitak, Jessica; Clegg, Tamara L.; Chetty, Marshini (November 2020, Media and Communication)

   null (Ed.)

   Researchers and policymakers advocate teaching children about digital privacy, but privacy literacy has not been theorized for children. Drawing on interviews with 30 families, including 40 children, we analyze children’s perspectives on password management in three contexts—family life, friendship, and education—and develop a new approach to privacy literacy grounded in Nissenbaum’s contextual integrity framework. Contextual integrity equates privacy with appropriate flows of information, and we show how children’s perceptions of the appropriateness of disclosing a password varied across contexts. We explain why privacy literacy should focus on norms rather than rules and discuss how adults can use learning moments to strengthen children’s privacy literacy. We argue that equipping children to make privacy-related decisions serves them better than instructing them to follow privacy-related rules. 

   more » « less