Contributed Talk Sessions | Poster Sessions | All Posters | Search Papers

Poster Session C: Friday, August 15, 2:00 – 5:00 pm, de Brug & E‑Hall

Predicting Response Inhibition: A Deep Learning Approach Using Pre-Response Single-Trial EEG Data

Anna Grabowska¹, Pawel Bason¹, Filip Sondej¹, Magdalena Senderecka¹; ¹Jagiellonian University in Krakow

Presenter: Anna Grabowska

Inhibitory control is a key component of executive functions. While it primarily depends on the extended motor network, early sensory processing of stimuli also plays a critical role in inhibition. This study examined whether deep neural networks could predict stop-signal task performance from early stop-related EEG signals in 225 participants, and whether including early go-related signals would enhance prediction accuracy. The best-performing model combined both go- and stop-related EEG data, revealing that successful inhibition was associated with reduced sensory processing of go stimuli and enhanced perception of stop signals. These results underscore the dynamic interplay between go and stop-signal processing and represent the first successful prediction of inhibition outcomes using non-motor EEG signals.

Topic Area: Predictive Processing & Cognitive Control

Extended Abstract: Full Text PDF