[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120660-en":3,"doc-seo-120660-105":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":20,"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},120660,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Improved decision making with similarity based machine learning - applications in chemistry","Experimental design decisions often suffer from severe data scarcity, which limits the usefulness of modern ready-made machine learning models that typically require large training sets. The work introduces similarity based machine learning to reduce data needs while enabling objective improvements for specific problem classes. After covering similarity learning for the harmonic oscillator and the Rosenbrock function, it demonstrates real-world applications under very scarce data conditions, including quantum chemistry-based molecular design, organic synthesis planning, and real estate investment decisions in Berlin.","arXiv :2205 .05633v3 [physics .chem-ph] 23 Nov 2022  \nImproved decision making with similarity based machine learning  \nDominik Lemm,1, 2 Guido Falk von Rudorff, 1 and O. Anatole von Lilienfeld3, 4, 5, a)  \n1) University of Vienna, Faculty of Physics, Kolingasse 14-16, AT-1090 Vienna, Austria  \n2) University of Vienna, Vienna Doctoral School in Physics, Boltzmanngasse 5, AT-1090 Vienna, Austria  \n3) Departments of Chemistry, Materials Science and Engineering, and Physics, University of Toronto, St. George Campus, Toronto, ON, Canada  \n4) Vector Institute forArtificial Intelligence, Toronto, ON, M5S 1M1, Canada  \n5) Machine Learning Group, Technische Universität Berlin and Institute for the Foundations of Learning and Data, 10587 Berlin, Germany  \n(Dated: 24 November 2022)  \nDespite their fundamental importance for science and society at large, experimental design decisions are often plagued by extreme data scarcity which severely hampers the use of modern ready-made machine learning models as they rely heavily on the paradigm, 'the bigger the data the better'. Presenting similarity based machine learning we show how to reduce these data needs such that decision making can be objectively improved in certain problem classes. After introducing similarity machine learning for the harmonic oscillator and the Rosenbrock function, we describe realworld applications to very scarce data scenarios which include (i) quantum mechanics based molecular design, (ii) organic synthesis planning, and (iii) real estate investment decisions in the city of Berlin, Germany.  \nI. INTRODUCTION  \nUseful answers to experimental design questions are crucial components for successful decision making under finite budget and time constraints. Conventionally, optimal or nearoptimal solutions are proposed by few expert scientists which severely limits humanity's `experimental reach', and even prevents us from solving global challenges in a timely fashion. Examples include addressing hunger, infectious disease, or climate change through catalysts for fertilizers, drugs, or renewable energy storage, respectively. High-dimensional combinatorial solution spaces pose a dramatic bottleneck for nonexpert scientists, and even in high-throughput scenarios. With the dawn of autonomous robotic experimentation in the chemical and biological sciences 1–6, humanity's experimental reach is revolutionized through the capacity in which experiments can be executed. Fostering the synergy between computational and experimental design, the digitization of the chemical and biological sciences facilitates data driven exploration through an accelerated feedback loop.  \nHowever, rigorous exploration algorithms are in dire need to bypass the combinatorial wall in the solution space. Conceptually, such experimental design exploration challenge falls into the realm of decision making theory.7,8 Developing improved decision making algorithms comprise dynamic or complex environments, and do require expert knowledge and numerous constraints posed by the problem's domain.  \nWith recent interests in data driven machine learning approaches surging, we have set out to investigate how to exploit modern statistical learning in order to assist with such decision making problems. Breakthroughs in machine learning and advances in data-availability through high performance computing or high-throughput experimentation are considered by some to represent a paradigm-shift, and could be seen as a  \na)Electronic mail: [anatole.vonlilienfeld@utoronto.ca](anatole.vonlilienfeld@utoronto.ca)  \nfourth pillar of scientific discovery.9–11 In particular, the availability of data has led to the establishment of a new paradigm'the bigger the data the better', which has become increasingly prevalent. Backed by the principles of statistical learning, the systematic decay of machine learning prediction errors with increasing training data supports this paradigm 12, 13 , and has even spurred the development of improved G","cbCaicRWYHMl3qgO","https://ap.wps.com/l/cbCaicRWYHMl3qgO","pdf",26490746,1,32,"English","en",105,"# Introduction\n## Data scarcity in experimental design\n## Similarity based machine learning concept\n## Similarity learning examples and applications","[{\"question\":\"Why is similarity based machine learning needed in experimental decision making?\",\"answer\":\"Experimental design often faces extreme data scarcity, which hampers standard machine learning models that rely on large datasets. Similarity based machine learning aims to reduce data requirements while improving decisions for certain problem classes.\"},{\"question\":\"What examples are used to introduce the similarity based approach?\",\"answer\":\"The document first introduces similarity machine learning for the harmonic oscillator and the Rosenbrock function, establishing the core idea before broader applications.\"},{\"question\":\"Which real-world application scenarios are discussed under scarce data conditions?\",\"answer\":\"The applications include quantum mechanics-based molecular design, organic synthesis planning, and real estate investment decisions in Berlin, Germany.\"}]","Improved decision making with similarity based machine learning - applications in chemistry | PDF",1785731209,81,{"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},"improved-decision-making-with-similarity-based-machine-learning-applications-in-chemistry","",{"@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/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/improved-decision-making-with-similarity-based-machine-learning-applications-in-chemistry/120660/",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","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is similarity based machine learning needed in experimental decision making?","Question",{"text":75,"@type":76},"Experimental design often faces extreme data scarcity, which hampers standard machine learning models that rely on large datasets. Similarity based machine learning aims to reduce data requirements while improving decisions for certain problem classes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What examples are used to introduce the similarity based approach?",{"text":80,"@type":76},"The document first introduces similarity machine learning for the harmonic oscillator and the Rosenbrock function, establishing the core idea before broader applications.",{"name":82,"@type":73,"acceptedAnswer":83},"Which real-world application scenarios are discussed under scarce data conditions?",{"text":84,"@type":76},"The applications include quantum mechanics-based molecular design, organic synthesis planning, and real estate investment decisions in Berlin, Germany.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},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":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]