Lecture
This lecture covers the application of Independent Component Analysis (ICA) in functional brain imaging, focusing on the transition from Principal Component Analysis (PCA) to ICA. Topics include the importance of non-Gaussianity, cleaning artefacts in fMRI, spatial versus temporal ICA, and the challenges in determining the number of components. The instructor explains the definition of ICA, its assumptions, and the difficulties in variance estimation and component ordering. Various ICA algorithms and their properties are discussed, along with the use of ICA for denoising and group studies. The lecture concludes with a critical note on ICA's properties and its role in exploring resting-state fMRI data.