Scroll Down

Time series classification models may be used to detect student interactions with virtual and tangible 3D models of dinosaur fossils on the basis of multiple sensor signals.

with Kirsten Butcher, University of Utah; Madlyn Runburg, Natural History Museum of Utah

Convolutional neural networks enables automated detection of motivational interviewing strategies between virtual avatars of therapists and clients. The technology being developed can enable personalized instruction with students, helping optimize the sequence of problems to attain skill mastery.

with Zac Imel, Mike Tanana, Jake Van Epps, University of Utah; Grin Lord, Dave Atkins, University of Washington

New domain modeling techniques enable intelligent systems to capture collective student interactions with information, allowing for optimizing information seeking and acquisition.

with Susanne Lajoie, McGill University; Tracy Dobie, Lauren Liang, University of Utah

Collaborate with an interdisciplinary team of learning scientists

Collaborate with an interdisciplinary team of learning scientists

Advanced Instructional Systems and Technologies laboratory

Our research focuses on how to improve the capability of technology-rich learning environments to adapt instruction to the specific needs of different learners. Adaptive instructional systems and technologies capture and analyze learner behaviors in real-time as a means to select and deliver the most suitable content.

Eric Poitras
Assistant Prof
Laurel Udy
Learning Sciences Grad
Kent Ellsworth
Learning Sciences Grad
Danny Aina
Learning Sciences Grad
Send us a message

Learn more about exciting and intellectually stimulating opportunities to tackle problems in he lab. Any questions about employment or funding proposals should be sent to Dr. Eric Poitras.