Beyond linear regression: mapping models in cognitive neuroscience should align with research goals

Anna Ivanova, Martin Schrimpf, Noga Zaslavsky, Evelina Fedorenko, MIT, United States; Stefano Anzellotti, Boston College, United States; Leyla Isik, Johns Hopkins University, United States

GAC Posters: Progress updates Poster

Late-breaking Research

Pacific Ballroom H-O

Presentation Time:
Thu, 25 Aug, 19:30 - 21:30 Pacific Time (UTC -8)

Many cognitive neuroscience studies use large feature sets to predict and interpret brain activity patterns. Feature sets take many forms, from human stimulus annotations to representations in deep neural networks. Of crucial importance in all these studies is the mapping model, which defines the space of possible relationships between features and neural data. Until recently, most encoding and decoding studies have used linear mapping models. Increasing availability of large datasets and computing resources has recently allowed some researchers to employ more flexible nonlinear mapping models instead; however, the question of whether nonlinear mapping models can yield meaningful scientific insights remains debated. We discuss the choice of a mapping model in the context of three overarching desiderata: predictive accuracy, interpretability, and biological plausibility. We show that, contrary to popular intuition, these desiderata do not map cleanly onto the linear/nonlinear divide; instead, each desideratum can refer to multiple research goals, each of which imposes its own constraints on the mapping model. Moreover, we argue that, instead of categorically treating the mapping models as linear or nonlinear, researchers should instead aim to estimate the complexity of these models.
No resources available.