Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2020.07.03.186288v1?rss=1 Authors: Caucheteux, C., KING, J.-R. Abstract: Deep learning has recently allowed substantial progress in language tasks such as translation and completion. Do such models process language similarly to humans, and is this similarity driven by systematic structural, functional and learning principles? To address these issues, we tested whether the activations of 7,400 artificial neural networks trained on image, word and sentence processing linearly map onto the hierarchy of human brain responses elicited during a reading task, using source-localized magneto-encephalography (MEG) recordings of one hundred and four subjects. Our results confirm that visual, word and language models sequentially correlate with distinct areas of the left-lateralized cortical hierarchy of reading. However, only specific subsets of these models converge towards brain-like representations during their training. Specifically, when the algorithms are trained on language modeling, their middle layers become increasingly similar to the late responses of the language network in the brain. By contrast, input and output word embedding layers often diverge away from brain activity during training. These differences are primarily rooted in the sustained and bilateral responses of the temporal and frontal cortices. Together, these results suggest that the compositional - but not the lexical - representations of modern language models converge to a brain-like solution. Copy rights belong to original authors. Visit the link for more info