[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128358-en":3,"doc-seo-128358-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128358,962085571259,"Theodora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Scaling up Machine Learning Models for fMRI Brain Encoding - Thesis","This Ph.D. thesis investigates techniques for optimizing brain encoding models with a focus on computational efficiency and scalability for large-scale functional magnetic resonance imaging (fMRI) datasets. Brain encoding predicts neural responses to complex stimuli by leveraging latent feature representations from artificial neural networks. The first study accelerates ridge regression using batch-parallelization with Dask, achieving up to 33× speedups on large fMRI datasets. The second study analyzes how dataset size and transformer model scaling affect encoding accuracy using vision Transformers trained on large-scale video game stimuli.","Scaling up Machine Learning Models for fMRI  \nBrain Encoding  \nSana Ahmadi  \nA Thesis  \nIn The Department of  \nComputer Science and Software Engineering  \nPresented in Partial Fulfillment of the Requirements For the Degree of Doctor of Philosophy Concordia University  \nMontr´eal, Qu´ebec, Canada  \nJanuary 2025  \n○c Sana Ahmadi, 2024  \nCONCORDIA UNIVERSITY  \nSchool of Graduate Studies  \nThis is to certify that the thesis prepared  \nBy: Sana Ahmadi  \nEntitled: Scaling up Machine Learning Models for fMRI Brain Encoding and submitted in partial fulfillment of the requirements for the degree of  \nDoctor of Philosophy (Computer Science)  \nComplies with the regulations of this University and meets the accepted standards with  \nrespect to originality and quality.  \nSigned by the Final Examining Committee:   Chair: Dr. Luis Amador Jimenez   External Examiner: Dr. Cyril Pernet   Examiner: Dr. Charalambos Poullis   Examiner Dr. Yiming Xiao   Examiner: Dr. Nizar Bouguila   Supervisor: Dr. Tristan Glatard   Co-supervisor: Dr. Pierre Lune Bellec  \nApproved by:  \nDr. Leila Kosseim, Graduate Program Director  \nJanuary 22, 2025    \nDr. Mourad Debbabi, Dean Gina Cody School of Engineering and Computer Science  \nAbstract  \nScaling up Machine Learning Models for fMRI Brain Encoding Sana Ahmadi, Ph.D.  \nConcordia University, 2024  \nThis thesis investigates techniques for optimizing brain encoding models, emphasizing computational efficiency and the scalability of both data and models within the framework of large-scale functional magnetic resonance imaging (fMRI) datasets. Brain encoding aims to predict neural responses to complex stimuli, such as video frames, by utilizing latent feature representations from artificial neural networks. The first study explores the acceleration of ridge regression, a widely used predictive model in brain encoding, particularly when applied to large fMRI datasets like the CNeuroMod Friends dataset. By implementing a novel batch-parallelization strategy using Dask, we achieved significant computational speedups of up to 33 × with 8 compute nodes and 32 threads compared to a single-threaded scikit-learn.  \nThe second study investigates how dataset size and model scaling affect brain encoding performance using vision Transformers. To do so, the VideoGPT model was trained end-to-end to extract spatiotemporal features from the Shinobi video game dataset with varying sample sizes (10K, 100K, 1M, and 6M) and model size (number of training parameters) . Ridge regression is then used to predict brain activity based on fMRI data and the extracted features from video games. Our results show that larger datasets lead to significantly improved encoding accuracy, with the 6M-sample dataset producing the highest Pearson correlation coefficients across subjects. Additionally, while increasing hidden layer dimensions in the transformer model greatly enhances performance, the number of attention heads appears to have a minimal effect. These findings emphasize the importance of data scaling for improving brain encoding, offering practical insights for optimizing neural network architectures in the context of large-scale stimuli data.  \nThis research advances the field of computationally efficient brain encoding, which is crucial for enhancing both computational speed and accuracy. These advancements are essential not only for improving our understanding of brain function but also for enabling scalable machine learning models on high-dimensional data and sophisticated stimuli, including applications in neuroprosthetics and clinical neuroscience.  \nAcknowledgment  \nFirst and foremost, I would like to express my gratitude to my wonderful research supervisors, Prof.Glatard and Prof.Bellec, for their invaluable support, guidance, and encouragement over the past years. Without their assistance and dedicated involvement in every step throughout the process, the success of this thesis would not be possible. I would also like to thank my coll","cbCaioehewSWc2T8","https://ap.wps.com/l/cbCaioehewSWc2T8","pdf",8828527,2,1,88,"English","en",105,"# Abstract\n## Optimization of ridge regression with Dask\n## Dataset and model scaling with vision Transformers\n## Contributions and significance","[{\"question\":\"What is the core goal of this thesis?\",\"answer\":\"The thesis aims to optimize brain encoding models by improving computational efficiency and scaling both datasets and models for large fMRI workloads.\"},{\"question\":\"How is ridge regression accelerated for brain encoding?\",\"answer\":\"A batch-parallelization strategy using Dask is used to accelerate ridge regression, enabling substantial speedups compared with single-threaded execution.\"},{\"question\":\"What factors most strongly improve brain encoding accuracy in the second study?\",\"answer\":\"Larger training datasets significantly improve encoding accuracy, while increasing transformer hidden dimensions strongly boosts performance; the number of attention heads shows minimal effect.\"}]","Scaling up Machine Learning Models for fMRI Brain Encoding - Thesis | PDF",1785947037,222,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"scaling-up-machine-learning-models-for-fmri-brain-encoding-thesis","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/scaling-up-machine-learning-models-for-fmri-brain-encoding-thesis/128358/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the core goal of this thesis?","Question",{"text":76,"@type":77},"The thesis aims to optimize brain encoding models by improving computational efficiency and scaling both datasets and models for large fMRI workloads.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is ridge regression accelerated for brain encoding?",{"text":81,"@type":77},"A batch-parallelization strategy using Dask is used to accelerate ridge regression, enabling substantial speedups compared with single-threaded execution.",{"name":83,"@type":74,"acceptedAnswer":84},"What factors most strongly improve brain encoding accuracy in the second study?",{"text":85,"@type":77},"Larger training datasets significantly improve encoding accuracy, while increasing transformer hidden dimensions strongly boosts performance; the number of attention heads shows minimal effect.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]