Spring is in the Air: New Research Findings from the WSC

SIOP 2022 Presentations

PARK lab graduate students, Sibley Lyndgaard, Corey Tatel, and Jennifer Egan, will be presenting on the research they have conducted in the past year at the 2022 SIOP Annual Conference. See below for the topics they will be presenting on.

Catastrophic interference in neural network models is mitigated when the training data reflect a power-law environmental structure

PARK Lab PhD students Sibley Lyndgaard and Lucas Provine will present a proceedings paper at the 44th Annual Cognitive Science Society conference in Toronto this July — see below for a brief summary of the paper’s findings.

In direct contrast to humans’ ability to learn increasingly complex skills across the lifespan, sequential learning in artificial neural networks is known to trigger catastrophic interference (CI), where previously learned skills are forgotten after learning new skills. We present a psychologically plausible approach for training neural networks which resolves major CI issues without the need to implement highly complex network architectures. Implications include the development of computational models for skill learning in humans.

Lyndgaard, S.F., Tidler, Z. R., Provine, L., & Varma, S. (in press). Catastrophic interference in neural network models is mitigated when the training data reflect a power-law environmental structure. In Proceedings of the 44th Annual Conference of the Cognitive Science Society. Toronto, CA: Cognitive Science Society.

ACPR 2022 Presentation

PARK Lab Research Assistant, Victoria Pham, presented her senior thesis titled “Influence of immigrant gneerational status on college major choice” at the first Annual Conference of Psychological Research hosted by the Psychology Department at the Georgia Institute of Technology on April 26, 2022.

Leave a Reply

Your email address will not be published.