[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-116959-en":3,"doc-seo-116959-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},116959,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",6,"Technology","Machine Learning with Chaotic Strange Attractors","Machine learning workloads demand substantial computational power to process massive datasets and train neural networks to high accuracy, making current approaches increasingly energy- and cost-intensive. To address the von Neumann bottleneck, an analog computing strategy is introduced that leverages chaotic nonlinear attractors for low-power machine learning. Inspired by neuromorphic computing, the platform is programmable and generalizable, using nonlinear mapping and sensitivity to initial conditions for effective clustering. Implemented as a simple analog device, it operates at milliwatt-scale power while achieving regression and classification results with low error and high accuracy.","Machine Learning with Chaotic Strange Attractors Bahadır Utku Kesgin and Uğur Teğin*  \nDepartment of Electrical and Electronics Engineering, Koç University, Istanbul, 34450, Turkey *corresponding author: [utegin@ku.edu.tr](utegin@ku.edu.tr)  \nAbstract  \nMachine learning studies need colossal power to process massive datasets and train neural networks to reach high accuracies, which have become gradually unsustainable. Limited by the von Neumann bottleneck, current computing architectures and methods fuel this high power consumption. Here, we present an analog computing method that harnesses chaotic nonlinear attractors to perform machine learning tasks with low power consumption. Inspired by neuromorphic computing, our model is a programmable, versatile, and generalized platform for machine learning tasks. Our mode provides exceptional performance in clustering by utilizing chaotic attractors' nonlinear mapping and sensitivity to initial conditions. When deployed as a simple analog device, it only requires milliwatt-scale power levels while being on par with current machine learning techniques. We demonstrate low errors and high accuracies with our model for regression and classification-based learning tasks.  \nIntroduction  \nCurrent computing methods and hardware limit machine learning studies and applications regarding speed , data resolution and deployed platforms. Particularly, the power consumption of artificial neural networks started to raise questions regarding its impact on the environment. Recent studies indicate that the carbon emissions of training a complex transformer learning model are roughly equivalent to the lifetime carbon emissions of five cars 1 , and training a famous language model consumed the energy required to charge 13,000 electric cars fully2. Several computing paradigms are proposed for machine learning studies to decrease training times and, therefore, the energy consumption issue. Among them, reservoir computing 3,4 offers a promising path by using nonlinear systems with fixed weights to process information in high dimensional space. Various neuromorphic devices5 were proposed to surpass chronic performance issues of conventional computing and high-power consumption issues. Optical computing methods6,7 and electronic memristive devices8–10 were introduced as powerful reservoir computing platforms. The concept of fixed nonlinear highdimensional mapping is of usual practice in several areas of machine learning , such as extreme learning machines 11 and support vector machines 12,13 .  \nIn machine learning studies, chaotic systems were mainly employed as targets to learn dynamical systems 14–16. Chaos theory examines deterministic but unpredictable dynamical systems that are extremely sensitive to initial conditions. These systems commonly occur in nature, inspiring art, science, and engineering 17. Also, chaotic spiking dynamics of neurons have inspired several neuromorphic machine learning applications18,19 . In the past, chaotic systems were proposed for Boolean computation  \nand data processing, forming the concept of chaos computing. Early chaos computing devices operated one-dimensional chaotic maps to perform logic operations20,21 . These dynamical systems were also suggested for reservoir computing but used in astable state just below the bifurcation point, where order transitions to chaos 22. Operating in a stable state, such systems could not benefit from chaos in learning and information processing for machine learning purposes. Following these attempts, systems with “weakly chaotic” architecture were proposed23,24 . However, these models and other similar approaches(25) could not demonstrate competent performances25.  \nHere, we propose an analog computing method based on controllable chaotic learning operators to perform high-dimensional nonlinear transformations on input data for machine learning purposes. Our method benefits circuits designed to compute chaotic strange attractors for r","cbCaiuIGGQFktJWL","https://ap.wps.com/l/cbCaiuIGGQFktJWL","pdf",1632025,1,19,"English","en",105,"# Abstract\n# Introduction\n# Results\n## Input / Output encoding and selection of the optimal attractor\n## The pattern and average divergence pace betwee","[{\"question\":\"Why does machine learning training become unsustainable with current hardware approaches?\",\"answer\":\"Training and achieving high accuracies require large computational power for massive datasets and neural network optimization, which increases power consumption and energy costs over time.\"},{\"question\":\"What is the proposed method for low-power machine learning?\",\"answer\":\"The method uses an analog computing platform that harnesses controllable chaotic nonlinear attractors to perform high-dimensional nonlinear transformations on input data.\"},{\"question\":\"How does the approach achieve competitive accuracy for learning tasks?\",\"answer\":\"Chaotic transformation exploits nonlinear mapping and sensitivity to initial conditions, improving learning performance for clustering, and enabling low-error regression and classification results.\"}]","Machine Learning with Chaotic Strange Attractors | PDF",1785672858,48,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-with-chaotic-strange-attractors","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-with-chaotic-strange-attractors/116959/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why does machine learning training become unsustainable with current hardware approaches?","Question",{"text":75,"@type":76},"Training and achieving high accuracies require large computational power for massive datasets and neural network optimization, which increases power consumption and energy costs over time.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the proposed method for low-power machine learning?",{"text":80,"@type":76},"The method uses an analog computing platform that harnesses controllable chaotic nonlinear attractors to perform high-dimensional nonlinear transformations on input data.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the approach achieve competitive accuracy for learning tasks?",{"text":84,"@type":76},"Chaotic transformation exploits nonlinear mapping and sensitivity to initial conditions, improving learning performance for clustering, and enabling low-error regression and classification results.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]