Finding the balance between model complexity and performance: Using ventral striatal oscillations to classify feeding behavior in rats - Fig 5

Performance of Population (black) and Individual (grey) models built from Baseline (A) and all condition (B) data and tested across states. A. Testing performance of population and individual models built from baseline data on all conditions (Inset). Population models built from Base do better than individual models when predicting behavior during any other condition than Base. B. Testing performance of population and individual models built from all conditions on all conditions (Inset). When models are built from all conditions, individual models do better than population models across conditions. * p < 0.05, ** p < 0.01, *** p < 0.001. Averages represented by circles and 95% confidence intervals by vertical bars.