{ "types" : { "Bookmark" : { "pluralLabel" : "Bookmarks" }, "Publication" : { "pluralLabel" : "Publications" }, "GoldStandardPublication" : { "pluralLabel" : "GoldStandardPublications" }, "GoldStandardBookmark" : { "pluralLabel" : "GoldStandardBookmarks" }, "Tag" : { "pluralLabel" : "Tags" }, "User" : { "pluralLabel" : "Users" }, "Group" : { "pluralLabel" : "Groups" }, "Sphere" : { "pluralLabel" : "Spheres" } }, "properties" : { "count" : { "valueType" : "number" }, "date" : { "valueType" : "date" }, "changeDate" : { "valueType" : "date" }, "url" : { "valueType" : "url" }, "id" : { "valueType" : "url" }, "tags" : { "valueType" : "item" }, "user" : { "valueType" : "item" } }, "items" : [ { "type" : "Bookmark", "id" : "https://puma.ub.uni-stuttgart.de/url/5f3b4d9e3f3b3ad075ce657789e8a14f/droessler", "tags" : [ "ai","artificial","deep","intelligence","learning","unternehmen","usa" ], "intraHash" : "5f3b4d9e3f3b3ad075ce657789e8a14f", "label" : "Cerebras", "user" : "droessler", "description" : "Cerebras is the go-to platform for fast and effortless AI training. Learn more at cerebras.ai.", "date" : "2025-04-14 15:42:20", "changeDate" : "2025-04-14 15:42:20", "count" : 1, "url" : "https://www.cerebras.ai/" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2152183f0edd23d3a6b697219f2c6ca41/inspo5", "tags" : [ "body","composition","deep","imaging","learning","machine","magnetic","medicine","musculoskeletal","resonance","sports","system" ], "intraHash" : "152183f0edd23d3a6b697219f2c6ca41", "interHash" : "3afe397a451bce869962d016312aff6a", "label" : "Quantification of training\u2010induced alterations in body composition via automated machine learning analysis of MRI images in the thigh region: A pilot study in young females", "user" : "inspo5", "description" : "", "date" : "2025-01-31 11:03:06", "changeDate" : "2025-02-11 20:13:39", "count" : 5, "pub-type": "article", "journal": "Physiological Reports","publisher":"Wiley", "year": "2025", "url": "http://dx.doi.org/10.14814/phy2.70187", "author": [ "Saied Ramedani","Ebru Kelesoglu","Norman Stutzig","Hendrik Von Tengg\u2010Kobligk","Keivan Daneshvar Ghorbani","Tobias Siebert" ], "authors": [ {"first" : "Saied", "last" : "Ramedani"}, {"first" : "Ebru", "last" : "Kelesoglu"}, {"first" : "Norman", "last" : "Stutzig"}, {"first" : "Hendrik", "last" : "Von Tengg\u2010Kobligk"}, {"first" : "Keivan", "last" : "Daneshvar Ghorbani"}, {"first" : "Tobias", "last" : "Siebert"} ], "editor": [ "Tobias Siebert" ], "editors": [ {"first" : "Tobias", "last" : "Siebert"} ], "volume": "13","number": "3","abstract": "AbstractThe maintenance of an appropriate ratio of body fat to muscle mass is essentialfor the preservation of health and performance, as excessive body fat is associatedwith an increased risk of various diseases. Accurate body composition assessmentrequires precise segmentation of structures. In this study we developed a novelautomatic machine learning approach for volumetric segmentation and quantita-tive assessment of MRI volumes and investigated the efficacy of using a machinelearning algorithm to assess muscle, subcutaneous adipose tissue (SAT), and bonevolume of the thigh before and after a strength training. Eighteen healthy, young,female volunteers were randomly allocated to two groups: intervention group(IG) and control group (CG). The IG group followed an 8-week strength endur-ance training plan that was conducted two times per week. Before and after thetraining, the subjects of both groups underwent MRI scanning. The evaluation ofthe image data was performed by a machine learning system which is based ona 3D U-Net- based Convolutional Neural Network. The volumes of muscle, bone,and SAT were each examined using a 2 (GROUP [IG vs. CG]) × 2 (TIME [pre-intervention vs. post-intervention]) analysis of variance (ANOVA) with repeatedmeasures for the factor TIME. The results of the ANOVA demonstrate significantTIME × GROUP interaction effects for the muscle volume (F1,16 = 12.80, p = 0.003,ηP2 = 0.44) with an increase of 2.93% in the IG group and no change in the CG(−0.62%, p = 0.893). There were no significant changes in bone or SAT volumebetween the groups. This study supports the use of artificial intelligence systemsto analyze MRI images as a reliable tool for monitoring training responses onbody composition.", "issn" : "2051-817X", "doi" : "10.14814/phy2.70187", "bibtexKey": "Ramedani_2025" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/297b7a2bc4cab9197afc612d1f46a01a2/sdnr", "tags" : [ "deep","inue","learning","myown","network","neural","ofdm","receiver" ], "intraHash" : "97b7a2bc4cab9197afc612d1f46a01a2", "interHash" : "eae26ff0298f818be94f791b8fa7a834", "label" : "Adaptive Neural Network-based OFDM Receivers", "user" : "sdnr", "description" : "", "date" : "2022-08-15 13:49:44", "changeDate" : "2022-08-16 12:00:44", "count" : 4, "pub-type": "inproceedings", "booktitle": "2022 IEEE 23rd International Workshop on Signal Processing Advances in Wireless Communication (SPAWC)", "year": "2022", "url": "https://ieeexplore.ieee.org/document/9833970", "author": [ "Moritz Benedikt Fischer","Sebastian Dörner","Sebastian Cammerer","Takayuki Shimizu","Hongsheng Lu","Stephan ten Brink" ], "authors": [ {"first" : "Moritz Benedikt", "last" : "Fischer"}, {"first" : "Sebastian", "last" : "Dörner"}, {"first" : "Sebastian", "last" : "Cammerer"}, {"first" : "Takayuki", "last" : "Shimizu"}, {"first" : "Hongsheng", "last" : "Lu"}, {"first" : "Stephan", "last" : "ten Brink"} ], "abstract": "We propose and examine the idea of continuously adapting state-of-the-art neural network (NN)-based orthogonal frequency division multiplex (OFDM) receivers to current channel conditions. This online adaptation via retraining is mainly motivated by two reasons: First, receiver design typically focuses on the universal optimal performance for a wide range of possible channel realizations. However, in actual applications and within short time intervals, only a subset of these channel parameters is likely to occur, as macro parameters, e.g., the maximum channel delay, can assumed to be static. Second, in-the-field alterations like temporal interferences or other conditions out of the originally intended specifications can occur on a practical (real-world) transmission. While conventional (filter-based) systems would require reconfiguration or additional signal processing to cope with these unforeseen conditions, NN-based receivers can learn to mitigate previously unseen effects even after their deployment. For this, we showcase on-the-fly adaption to current channel conditions and temporal alterations solely based on recovered labels from an outer forward error correction (FEC) code without any additional piloting overhead. To underline the flexibility of the proposed adaptive training, we showcase substantial gains for scenarios with static channel macro parameters, for out-of-specification usage and for interference compensation.", "doi" : "10.1109/SPAWC51304.2022.9833970", "bibtexKey": "FischerAdaptiveRX2022" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/22aa5c2e2130e2c35819a1893b379ef8f/felixholm", "tags" : [ "architecture","cholec80","deep","laparoscopic","learning","videos" ], "intraHash" : "2aa5c2e2130e2c35819a1893b379ef8f", "interHash" : "1baa07bbf780767569f8a0a9e4f88433", "label" : "EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic\r\n Videos", "user" : "felixholm", "description" : "[1602.03012] EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos", "date" : "2021-08-08 22:28:14", "changeDate" : "2021-08-08 20:28:14", "count" : 2, "pub-type": "misc", "year": "2016", "url": "http://arxiv.org/abs/1602.03012", "author": [ "Andru P. Twinanda","Sherif Shehata","Didier Mutter","Jacques Marescaux","Michel de Mathelin","Nicolas Padoy" ], "authors": [ {"first" : "Andru P.", "last" : "Twinanda"}, {"first" : "Sherif", "last" : "Shehata"}, {"first" : "Didier", "last" : "Mutter"}, {"first" : "Jacques", "last" : "Marescaux"}, {"first" : "Michel", "last" : "de Mathelin"}, {"first" : "Nicolas", "last" : "Padoy"} ], "note": "cite arxiv:1602.03012Comment: Video: https://www.youtube.com/watch?v=6v0NWrFOUUM","abstract": "Surgical workflow recognition has numerous potential medical applications,\r\nsuch as the automatic indexing of surgical video databases and the optimization\r\nof real-time operating room scheduling, among others. As a result, phase\r\nrecognition has been studied in the context of several kinds of surgeries, such\r\nas cataract, neurological, and laparoscopic surgeries. In the literature, two\r\ntypes of features are typically used to perform this task: visual features and\r\ntool usage signals. However, the visual features used are mostly handcrafted.\r\nFurthermore, the tool usage signals are usually collected via a manual\r\nannotation process or by using additional equipment. In this paper, we propose\r\na novel method for phase recognition that uses a convolutional neural network\r\n(CNN) to automatically learn features from cholecystectomy videos and that\r\nrelies uniquely on visual information. In previous studies, it has been shown\r\nthat the tool signals can provide valuable information in performing the phase\r\nrecognition task. Thus, we present a novel CNN architecture, called EndoNet,\r\nthat is designed to carry out the phase recognition and tool presence detection\r\ntasks in a multi-task manner. To the best of our knowledge, this is the first\r\nwork proposing to use a CNN for multiple recognition tasks on laparoscopic\r\nvideos. Extensive experimental comparisons to other methods show that EndoNet\r\nyields state-of-the-art results for both tasks.", "bibtexKey": "twinanda2016endonet" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2a505ebafced08b14d297c0ce1cbc64cf/lizhong", "tags" : [ "Analysis","Data","Deep","Learning","Stream","myown" ], "intraHash" : "a505ebafced08b14d297c0ce1cbc64cf", "interHash" : "45cafd5d8e7ec1c78e844491101d4286", "label" : "A Method for Stream Data Analysis", "user" : "lizhong", "description" : "", "date" : "2021-07-15 12:40:53", "changeDate" : "2021-07-15 10:53:13", "count" : 1, "pub-type": "article", "journal": "Sustained Simulation Performance 2019 and 2020: Proceedings of the Joint Workshop on Sustained Simulation Performance, University of Stuttgart (HLRS) and Tohoku University, 2019 and 2020", "year": "2020", "url": "", "author": [ "Li Zhong" ], "authors": [ {"first" : "Li", "last" : "Zhong"} ], "pages": "111", "bibtexKey": "zhong2020method" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/22b1e88a38053728e10241b1433cc3f08/lizhong", "tags" : [ "Deep","HPC","Learning","myown" ], "intraHash" : "2b1e88a38053728e10241b1433cc3f08", "interHash" : "10d1fadba3a175f076357cc0bd6762f2", "label" : "On the Detection and Interpretation of Performance Variations of HPC Applications", "user" : "lizhong", "description" : "", "date" : "2021-07-15 12:36:43", "changeDate" : "2021-07-15 10:54:20", "count" : 2, "pub-type": "incollection", "booktitle": "Sustained Simulation Performance 2018 and 2019","publisher":"Springer", "year": "2020", "url": "", "author": [ "Dennis Hoppe","Li Zhong","Stefan Andersson","Diana Moise" ], "authors": [ {"first" : "Dennis", "last" : "Hoppe"}, {"first" : "Li", "last" : "Zhong"}, {"first" : "Stefan", "last" : "Andersson"}, {"first" : "Diana", "last" : "Moise"} ], "pages": "41--56", "bibtexKey": "hoppe2020detection" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2f698e236a380faddfb8f96d98b28f5bc/inue", "tags" : [ "myown","network;over-the-air;software-defined","software-defined","from:sdnr","transmissions;open-source","(artificial","systems;block-based","module;transmitter","transmission;receiver","implementations;deep","computing;two-step","nets;radio","intelligence);neural","libraries;continuous","learning;communications","learning;end-to-end","rate;over-the-air","synchronization;frame","error","transmissions;receiver","deep","neural","software","synchronization","data","learning;modulation;neural","learning","libraries;software","radio","implementations;off-the-shelf","networks;NNs;block","procedure;end-to-end","radio;synchronisation;telecommunication","radios;Training;Receivers;Communication","networks;Hardware;Transmitters;Synchronization;Autoencoder;communication;deep","receivers;software","systems;Artificial" ], "intraHash" : "f698e236a380faddfb8f96d98b28f5bc", "interHash" : "a0e38e6df23c2f25303e9abd1d9fd60d", "label" : "Deep Learning Based Communication Over the Air", "user" : "inue", "description" : "", "date" : "2020-03-20 15:07:06", "changeDate" : "2020-03-20 14:07:06", "count" : 3, "pub-type": "article", "journal": "IEEE Journal of Selected Topics in Signal Processing", "year": "2018", "url": "", "author": [ "S. Dörner","S. Cammerer","J. Hoydis","S. ten Brink" ], "authors": [ {"first" : "S.", "last" : "Dörner"}, {"first" : "S.", "last" : "Cammerer"}, {"first" : "J.", "last" : "Hoydis"}, {"first" : "S.", "last" : "ten Brink"} ], "volume": "12","number": "1","pages": "132-143", "issn" : "1941-0484", "doi" : "10.1109/JSTSP.2017.2784180", "bibtexKey": "learning_to_communicate" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/24ababf2563d41181e61df0741cff5388/tobiasschwinn", "tags" : [ "deep","learning","ml","things","useful" ], "intraHash" : "4ababf2563d41181e61df0741cff5388", "interHash" : "28f49d94d3029e886460cde63094e482", "label" : "A few useful things to know about machine learning", "user" : "tobiasschwinn", "description" : "", "date" : "2019-11-22 11:46:18", "changeDate" : "2019-11-22 10:46:18", "count" : 2, "pub-type": "article", "journal": "Communications of the ACM","publisher":"ACM","address":"New York, NY, USA", "year": "2012", "url": "http://doi.acm.org/10.1145/2347736.2347755 http://dl.acm.org/citation.cfm?doid=2347736.2347755", "author": [ "Pedro Domingos" ], "authors": [ {"first" : "Pedro", "last" : "Domingos"} ], "volume": "55","number": "10","pages": "78", "mendeley-groups" : "Machine Learning", "mendeley-tags" : "ml,deep learning", "file" : ":C$\\backslash$:/Users/localicdtschw/Documents/Mendeley Desktop/Domingos/Communications of the ACM/Domingos - 2012 - A few useful things to know about machine learning.pdf:pdf", "issn" : "00010782", "doi" : "10.1145/2347736.2347755", "bibtexKey": "Domingos:2012:FUT:2347736.2347755" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/20dd4f68022572e8f39dd6301d4b54b30/michaelneumann", "tags" : [ "deep","learning" ], "intraHash" : "0dd4f68022572e8f39dd6301d4b54b30", "interHash" : "7ac32ab2e057845545d5bd502f0e4a85", "label" : "Deep Learning", "user" : "michaelneumann", "description" : "", "date" : "2018-02-19 14:58:22", "changeDate" : "2018-02-19 13:58:22", "count" : 1, "pub-type": "unpublished", "year": "2016", "url": "http://www.deeplearningbook.org", "author": [ "Ian Goodfellow Yoshua Bengio","Aaron Courville" ], "authors": [ {"first" : "Ian Goodfellow Yoshua", "last" : "Bengio"}, {"first" : "Aaron", "last" : "Courville"} ], "note": "Book in preparation for MIT Press", "date-added" : "2016-06-06 10:16:02 +0000", "date-modified" : "2016-12-02 15:03:40 +0000", "bdsk-url-1" : "http://www.deeplearningbook.org", "bibtexKey": "goodfellow2016deep" } ] }