Abstract The Spatio-Temporal Representation of Nat Machine Lear Carnegie M lweh My thesis is about studying how the brain organizes complex information when it read text in a naturalistic setting. My work is an integrated interdisciplinary effort which employs functional neuroimaging, and revolves around the development of machine learning methods to uncover multilayer cognitive processes from brain activity recordings. Studying how the human brain represents meaning is not only important for expanding our scientific knowledge of the brain and of intelligence. By mapping behavioral traits to dif-ferences in brain representations, we increase our understanding of neurological disorders that plague large populations, which may bring us closer to finding treatments (as detailed in the last section of this statement). For all these purposes,functional neuroimaging is an invaluable tool. Traditional functional neuroimaging studies typically consist of highly controlled experiments which vary along a few conditions. The stimuli for these conditions are artificially designed, and therefore might result in conclusions that are not generalizable to how the brain works in real life. When studying language processing for example, very few experiments show subjects a real text, and show instead carefullydesigned stimuli. Furthermore, the analysis of functional neuroimaging datahas typically consisted in simple comparisons: regions whichrespond differently to the individual conditions are identifiedMany researchers have recently started using brain decoding(i.e. classifying the stimulus being processed from the sub-ject’s brain image), which can reveal responses encoded insubtle patterns of activity across a brain region. However,brain decoding is still mostly used in a rather limited fashionIn order to predict which condition an image corresponds to,a classifier is trained on several examples of each condition.This classifier is not able to generalize its knowledge to noveconditions not seen in training. It can therefore be arguedthat such a model does not represent a broad understandingof brain function. This work revolves around studying the parallel cognitiveprocesses involved when subjects are engaged in a naturalistic language processing task, namely reading a chapter of a real book. We use computational linguistics algorithms to model the content of the text, and machine learning to identify regions in the brain that are involved in processing its dferent components. This work is consequently an integrated interdisciplinary effort.