{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/modeling-cognitive-deficits-following","title":"Modeling cognitive deficits following neurodegenerative diseases and traumatic brain injuries with deep convolutional neural networks","arxiv_id":"1612.04423","date":"2016-12-13","proceeding":null,"authors":["Bethany Lusch","Jake Weholt","Pedro D. Maia","J. Nathan Kutz"],"abstract":"The accurate diagnosis and assessment of neurodegenerative disease and\ntraumatic brain injuries (TBI) remain open challenges. Both cause cognitive and\nfunctional deficits due to focal axonal swellings (FAS), but it is difficult to\ndeliver a prognosis due to our limited ability to assess damaged neurons at a\ncellular level in vivo. We simulate the effects of neurodegenerative disease\nand TBI using convolutional neural networks (CNNs) as our model of cognition.\nWe utilize biophysically relevant statistical data on FAS to damage the\nconnections in CNNs in a functionally relevant way. We incorporate energy\nconstraints on the brain by pruning the CNNs to be less over-engineered.\nQualitatively, we demonstrate that damage leads to human-like mistakes. Our\nexperiments also provide quantitative assessments of how accuracy is affected\nby various types and levels of damage. The deficit resulting from a fixed\namount of damage greatly depends on which connections are randomly injured,\nproviding intuition for why it is difficult to predict impairments. There is a\nlarge degree of subjectivity when it comes to interpreting cognitive deficits\nfrom complex systems such as the human brain. However, we provide important\ninsight and a quantitative framework for disorders in which FAS are implicated.","url_abs":"http://arxiv.org/abs/1612.04423v1","url_pdf":"http://arxiv.org/pdf/1612.04423v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"modeling-cognitive-deficits-following","repo_url":"https://github.com/BethanyL/damaged_cnns","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"prognosis","task_name":"Prognosis"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}