Optimizing Memory using Neural Information (OMNI)
The goal of the OMNI project is to develop a computational framework for the prediction and optimization of human memory which is informed by indirect measurements of brain activity. Simply put, we aim to record people's brains while they learn things, predict which things they learned successfully and which they didn't, and then devise better ways to teach them. The project applies state of the art in machine learning and cognitive modeling methods to the design of next-generation intelligent tutoring systems.
Papers & Resources
- Paper Identifying Causal Subsequent Memory Effects
- Paper Getting Blood from a Stone: Improving Neural Inferences without Additional Neural Data
- Paper Knowledge Tracing Using the Brain (EDM 2018)
- Paper Modeling Second-Language Learning from a Psychological Perspective (NAACL-HLT 2018)
- Paper A neuro-cognitive model for predicting the fate of individual memories (CogSci 2018)
- Abstract A Hierarchical Bayesian Approach to Inferring Mnemonic Status from the Brain (CCN 2017)
- Abstract Predicting memory performance using a joint model of brain and behavior (CCN 2018)
- Data OSF Project Homepage
Team
- Shannon Tubridy (Post-doc)
- Todd Gureckis (PI)
- Lila Davachi (Co-PI)
- David Halpern (PhD Student)
- Pam Osborn Popp (PhD Student)
- Camille Gasser (Research Assistant)
- Mike Mozer (Advisor/Consultant)
Support
The project was supported by National Science Foundation grant DRL-1631436 and by a startup grant from the NYU College of Arts and Science.