How do thoughts, sensations, decisions, emotions, arise from neural activity? What is the biology underlying a social psychiatric disorder such as autism? These questions are answered in cognitive neuroscience via experimental psychology. Unlike physics, cognitive psychology does not rely on first principles. However, brain imaging provides quantitative measurements that can build or constrain model of brain function.
I will discuss how we use build machine learning tools to help understanding the link between the brain, the organe, and the mind, our mental world. I will quickly introduce key concepts of machine learning, seen as high-dimensional statistics, fitting ill-constrained models. I will present progress on "brain reading", inferring thoughts from brain signals. Blind mining algorithms can be used to uncover intrinsic brain structure in the absence of controlled thoughts. From a computational statistics standpoint, the key point is to find the right tradeoff between injecting structure to constrain the model, and capturing new information from the data. Going one step further, we assemble these tools to refine representations of cognition from brain data.
Beyond cognitive neuroscience, data-intensive investigations open the door to quantitative research in new fields. But it requires a shift in scientific methodology: redefining the accepted notion of a model, reinventing validation without experimental intervention, linking data-driven findings to non-formalized domain knowledge.