More Like this

1. A Bandit you can Trust.

   Prihar, E. (June 2023, Proceedings of The 31st ACM Conference On User Modeling, Adaptation And Personalization)

   This work proposes Dynamic Linear Epsilon-Greedy, a novel con- textual multi-armed bandit algorithm that can adaptively assign personalized content to users while enabling unbiased statistical analysis. Traditional A/B testing and reinforcement learning ap- proaches have trade-offs between empirical investigation and max- imal impact on users. Our algorithm seeks to balance these objec- tives, allowing platforms to personalize content effectively while still gathering valuable data. Dynamic Linear Epsilon-Greedy was evaluated via simulation and an empirical study in the ASSIST- ments online learning platform. In simulation, Dynamic Linear Epsilon-Greedy performed comparably to existing algorithms and in ASSISTments, slightly increased students’ learning compared to A/B testing. Data collected from its recommendations allowed for the identification of qualitative interactions, which showed high and low knowledge students benefited from different content. Dynamic Linear Epsilon-Greedy holds promise as a method to bal- ance personalization with unbiased statistical analysis. All the data collected during the simulation and empirical study are publicly available at https://osf.io/zuwf7/. 

   more » « less
2. A Bandit You Can Trust

   https://doi.org/10.1145/3565472.3592955  

   Prihar, Ethan; Sales, Adam; Heffernan, Neil (July 2023, UMAP 2023)

   This work proposes Dynamic Linear Epsilon-Greedy, a novel contextual multi-armed bandit algorithm that can adaptively assign personalized content to users while enabling unbiased statistical analysis. Traditional A/B testing and reinforcement learning approaches have trade-offs between empirical investigation and maximal impact on users. Our algorithm seeks to balance these objectives, allowing platforms to personalize content effectively while still gathering valuable data. Dynamic Linear Epsilon-Greedy was evaluated via simulation and an empirical study in the ASSISTments online learning platform. In simulation, Dynamic Linear Epsilon-Greedy performed comparably to existing algorithms and in ASSISTments, slightly increased students’ learning compared to A/B testing. Data collected from its recommendations allowed for the identification of qualitative interactions, which showed high and low knowledge students benefited from different content. Dynamic Linear Epsilon-Greedy holds promise as a method to balance personalization with unbiased statistical analysis. All the data collected during the simulation and empirical study are publicly available at https://osf.io/zuwf7/. 

   more » « less
3. Can a Transformer Represent a Kalman Filter?

   Goel, Gautam; Bartlett, Peter (July 2024, Learning for Dynamics and Control (L4DC) conference 2024)
4. A PUF Based CAN Security Framework

   https://doi.org/10.1109/ISVLSI49217.2020.00094  

   Cultice, Tyler; Labrado, Carson; Thapliyal, Himanshu (July 2020, 2020 IEEE Computer Society Annual Symposium on VLSI (ISVLSI))

   null (Ed.)

   We propose a method to include security and reliability to the messages sent over the CAN bus. Our approach adheres to CAN standard ISO 11898-1. A reliable PUF response is used in key generation to create a unique shared AES-256 key between each ECU, allowing for all message paths to be encrypted. In addition, an HMAC system with a counter is implemented to help protect against replay attacks and message tampering within the network. 

   more » « less
5. Discourse Can Create a Learning Culture

   https://doi.org/10.5951/MTLT.2019.0351  

   Curtis, Kelly; Lindo, Katrina; Jansen, Amanda (January 2021, Mathematics Teacher: Learning and Teaching PK-12)

   When a ninth-grade teacher used discourse moves aligned with responding to students’ thinking and explicitly promoting productive dispositions, her students reported having positive experiences. 

   more » « less