[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126095-en":3,"doc-seo-126095-105":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":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":20},126095,5909887256941,"Levi","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Axion-Like-Particle Search Using Machine Learning for the Signal Sensitivity Optimization with Run-2 LHC Data - Reviewer’s Opinion of Final Thesis","Reviewer’s opinion evaluating a bachelor thesis on an axion-like particle search using machine learning for signal sensitivity optimization with Run-2 LHC data recorded by the ATLAS experiment. The reviewer confirms the thesis meets its assignments and is technically correct with minor exceptions. The model training analysis is considered highly convincing, and the thesis is well structured with clear writing and adequate references. Open questions focus on network architecture optimality, binary classifier formulation, learning-curve behavior, feature-importance computation, and formalizing optimization with additional object states.","REVIEWER‘S OPINION OF FINAL THESIS  \nI. IDENTIFICATION DATA  \nThesis name: Axion-Like-Particle Search Using Machine Learning for the Signal  \nSensitivity Optimization with Run-2 LHC Data Recorded by the ATLAS Experiment  \nAuthor’s name: Ondřej Matoušek  \nType of thesis : bachelor  \nFaculty/Institute: Faculty of Electrical Engineering  \nDepartment: Department of Cybernetics  \nThesis reviewer: Boris Flach  \nReviewer’s department: Department of Cybernetics  \nII. EVALUATION OF INDIVIDUAL CRITERIA  \n\n| Assignment ordinarily challenging\u003Cbr>Evaluation of thesis difficulty of assignment. |\n| --- |\n| Overall, the level of difficulty of the task was normally challenging. On the one hand, the application domain required the student to become familiar with the basics of particle physics and the specifics of hadron collision detectors. On the other hand, the machine learning concepts required to solve the task, were moderately challenging. |\n\n\n| Satisfaction of assignment fulfilled\u003Cbr>Assess that handed thesis meets assignment. Present points of assignment that fell short or were extended. Try to assess importance, impact or cause of each shortcoming. |\n| --- |\n| The submitted thesis meets the task assignments. |\n\n\n| Method of conception correct\u003Cbr>Assess that student has chosen correct approach or solution methods. |\n| --- |\n| The proposed method is technically correct, however, with minor exceptions. It remains unclear for me, whether the used network architecture is already optimally chosen. The thorough analysis of the trained model is on the other hand very convincing. |\n\n\n| Technical level B-very good.\u003Cbr>Assess level of thesis specialty, use of knowledge gained by study and by expert literature, use of sources and data gained by experience. |\n| --- |\n| The technical level of the thesis is adequate. |\n\n\n| Formal and language level, scope of thesis B-very good.\u003Cbr>Assess correctness of usage of formal notation. Assess typographical and language arrangement of thesis. |\n| --- |\n| The thesis is in most parts well structured and clearly written. |\n\n\n| Selection of sources, citation correctness B-very good.\u003Cbr>Present your opinion to student’s activity when obtaining and using study materials for thesis creation. Characterizeselection of sources. Assess that student used all relevant sources. Verify that all used elements are correctly distinguished from own results and thoughts. Assess that citation ethics has not been breached and that all bibliographic citations are complete and in accordance with citation convention and standards. |\n| --- |\n| The references are adequate. Existing work is clearly distinguished from own results of the student. |\n\nREVIEWER‘S OPINION OF FINAL THESIS  \n\n| Additional commentary and evaluation\u003Cbr>Present your opinion to achieved primary goals of thesis, e.g. level of theoretical results, level and functionality of technical or software conception, publication performance, experimental dexterity etc. |\n| --- |\n| The presented thesis is mostly well written, clearly structured and technically correct. However, there remain a few open questions and issues.\u003Cbr>(1) Is the analysis of the feature distributions (section 4 .3. 1) used in the design of the classifier network?\u003Cbr>(2) The proposed network is essentially a binary classifier. Why are you using two outputs, softmax and cross entropy? Equivalently, you could use one output, sigmoid and binary cross entropy.\u003Cbr>(3) The presented learning curves (figure 4 .6) show no overfitting and at the same time quite large loss values. Have you tried to use larger architectures?\u003Cbr>(4) What do you mean by \"optimising the capabilities of a (trained) classifier\"? (section 4 .4.2)\u003Cbr>(5) It might seem that computing Shapley values for individual features will require re-training of the network for different feature combinations. How is this avoided?\u003Cbr>(6) Do you see a way how to formalise the task of model optimisation w. r.t. additional object states (here signal mass) wh","cbCaiialZ5F4IxYX","https://ap.wps.com/l/cbCaiialZ5F4IxYX","pdf",126576,5,1,2,"English","en",105,"# I. Identification Data\n## Thesis information\n# II. Evaluation of Individual Criteria\n## Thesis difficulty\n## Assignment fulfillment\n## Method correctness\n## Technical level\n## Formal and language level\n## Sources and citation correctness\n# III. Overall Evaluation and Questions for Defense\n## Overall grade and defense questions","[{\"question\":\"Does the thesis meet the assigned bachelor graduation criteria?\",\"answer\":\"Yes. The reviewer states that the submitted thesis fulfils the task assignments and clearly meets bachelor graduation work criteria.\"},{\"question\":\"What technical aspects receive positive assessment, despite minor concerns?\",\"answer\":\"The proposed method is technically correct with minor exceptions. The thorough analysis of the trained model is described as very convincing, and the thesis is mostly well written, clearly structured, and technically correct.\"},{\"question\":\"Which open questions does the reviewer raise for the defense?\",\"answer\":\"The reviewer asks about feature-distribution usage in the classifier design, the choice of two outputs for a binary task, learning curves with large loss values, how classifier capability optimization is defined, avoidance of retraining when computing Shapley values, and formalization of optimization using additional training-time object states.\"}]","Axion-Like-Particle Search Using Machine Learning for the Signal Sensitivity Optimization with Run-2 LHC Data - Reviewer’s Opinion of Final Thesis | PDF",1785903066,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":29},"axion-like-particle-search-using-machine-learning-for-the-signal-sensitivity-optimization-with-run-2-lhc-data-reviewers-opinion-of-final-thesis","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":22},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/axion-like-particle-search-using-machine-learning-for-the-signal-sensitivity-optimization-with-run-2-lhc-data-reviewers-opinion-of-final-thesis/126095/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",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},"Does the thesis meet the assigned bachelor graduation criteria?","Question",{"text":75,"@type":76},"Yes. The reviewer states that the submitted thesis fulfils the task assignments and clearly meets bachelor graduation work criteria.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What technical aspects receive positive assessment, despite minor concerns?",{"text":80,"@type":76},"The proposed method is technically correct with minor exceptions. The thorough analysis of the trained model is described as very convincing, and the thesis is mostly well written, clearly structured, and technically correct.",{"name":82,"@type":73,"acceptedAnswer":83},"Which open questions does the reviewer raise for the defense?",{"text":84,"@type":76},"The reviewer asks about feature-distribution usage in the classifier design, the choice of two outputs for a binary task, learning curves with large loss values, how classifier capability optimization is defined, avoidance of retraining when computing Shapley values, and formalization of optimization using additional training-time object states.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":20,"slug":137},19,"General","general"]