Learn and apply cutting-edge data analysis techniques for "big neurodata" (theory and MATLAB/Python code)
InstructorMike X CohenEditorial course preview
These 2 complementary views highlight concrete, legible examples from the course presentation.
This composite slide illustrates multivariate signal processing concepts by combining the Rayleigh quotient formula, its 3D geometric visualization, and a schematic mapping latent sources to sensors.
This slide illustrates the application of multivariate signal processing to neural data, featuring an EEG head model, a Rayleigh quotient formula, and a topographic plot.
The curriculum moves from foundational linear algebra into advanced topics like covariance matrices, PCA, and ICA, including statistical validation via overfitting and permutation testing.
Practical application is integrated through specific tasks, such as performing PCA on non-phase-locked data and two-stage source separation using real EEG data.
The primary exercise implementation is in MATLAB; while Python code is mentioned, there is an absence of dedicated Python solution files for the exercises. One signal from 2023 suggests this gap exists, but this review predates the displayed update date; the update may have addressed it, but the update label does not prove that it was corrected.
The curriculum aligns well with the needs of neuroscientists and mathematicians requiring a linear algebra foundation.
