Explores advanced techniques in multilevel modeling, including fitting separate models, estimating coefficients, and checking residuals for model evaluation.
Covers regression diagnostics for linear models, emphasizing the importance of checking assumptions and identifying outliers and influential observations.
Explores the provable benefits of overparameterization in model compression, emphasizing the efficiency of deep neural networks and the importance of retraining for improved performance.
By Meenakshi Khosla explores data-driven modeling in large-scale naturalistic neuroscience, focusing on brain activity representation and computational models.
