Pub Date : 2022-01-01DOI: 10.1007/978-3-662-62492-0_16
David H. Freedman
{"title":"Auf der Jagd nach neuen Medikamenten","authors":"David H. Freedman","doi":"10.1007/978-3-662-62492-0_16","DOIUrl":"https://doi.org/10.1007/978-3-662-62492-0_16","url":null,"abstract":"","PeriodicalId":45413,"journal":{"name":"Kunstliche Intelligenz","volume":"61 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"51381436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-662-62492-0_17
Eva Wolfangel
{"title":"DeepMind will Problem der Proteinfaltung gelöst haben","authors":"Eva Wolfangel","doi":"10.1007/978-3-662-62492-0_17","DOIUrl":"https://doi.org/10.1007/978-3-662-62492-0_17","url":null,"abstract":"","PeriodicalId":45413,"journal":{"name":"Kunstliche Intelligenz","volume":"1 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"51381443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-662-62492-0_4
Anna von Hopffgarten
{"title":"Maschinen das Träumen lehren","authors":"Anna von Hopffgarten","doi":"10.1007/978-3-662-62492-0_4","DOIUrl":"https://doi.org/10.1007/978-3-662-62492-0_4","url":null,"abstract":"","PeriodicalId":45413,"journal":{"name":"Kunstliche Intelligenz","volume":"27 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"51381916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-662-62492-0_3
Alison Gopnik
{"title":"Lernen wie ein Kind","authors":"Alison Gopnik","doi":"10.1007/978-3-662-62492-0_3","DOIUrl":"https://doi.org/10.1007/978-3-662-62492-0_3","url":null,"abstract":"","PeriodicalId":45413,"journal":{"name":"Kunstliche Intelligenz","volume":"4 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"51381892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-662-62492-0_24
Eva Wolfangel
{"title":"Fehler haben Konsequenzen für das Leben echter Menschen","authors":"Eva Wolfangel","doi":"10.1007/978-3-662-62492-0_24","DOIUrl":"https://doi.org/10.1007/978-3-662-62492-0_24","url":null,"abstract":"","PeriodicalId":45413,"journal":{"name":"Kunstliche Intelligenz","volume":"1 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"51381860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents a framework for learning event sequences for anomaly detection in a smart home environment. It addresses environment conditions, device grouping, system performance and explainability of anomalies. Our method models user behavior as sequences of events, triggered by interaction of the home residents with the Internet of Things (IoT) devices. Based on a given set of recorded event sequences, the system can learn the habitual behavior of the residents. An anomaly is described as deviation from that normal behavior, previously learned by the system. One key feature of our framework is the explainability of detected anomalies, which is implemented through a simple rule analysis.
{"title":"A Framework for Learning Event Sequences and Explaining Detected Anomalies in a Smart Home Environment.","authors":"Justin Baudisch, Birte Richter, Thorsten Jungeblut","doi":"10.1007/s13218-022-00775-5","DOIUrl":"https://doi.org/10.1007/s13218-022-00775-5","url":null,"abstract":"<p><p>This paper presents a framework for learning event sequences for anomaly detection in a smart home environment. It addresses environment conditions, device grouping, system performance and explainability of anomalies. Our method models user behavior as sequences of events, triggered by interaction of the home residents with the Internet of Things (IoT) devices. Based on a given set of recorded event sequences, the system can learn the habitual behavior of the residents. An anomaly is described as deviation from that normal behavior, previously learned by the system. One key feature of our framework is the explainability of detected anomalies, which is implemented through a simple rule analysis.</p>","PeriodicalId":45413,"journal":{"name":"Kunstliche Intelligenz","volume":"36 3-4","pages":"259-266"},"PeriodicalIF":2.9,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9619011/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10814177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/s13218-022-00781-7
Bettina Finzel, Anna Saranti, Alessa Angerschmid, David Tafler, Bastian Pfeifer, Andreas Holzinger
Graph Neural Networks (GNN) show good performance in relational data classification. However, their contribution to concept learning and the validation of their output from an application domain's and user's perspective have not been thoroughly studied. We argue that combining symbolic learning methods, such as Inductive Logic Programming (ILP), with statistical machine learning methods, especially GNNs, is an essential forward-looking step to perform powerful and validatable relational concept learning. In this contribution, we introduce a benchmark for the conceptual validation of GNN classification outputs. It consists of the symbolic representations of symmetric and non-symmetric figures that are taken from a well-known Kandinsky Pattern data set. We further provide a novel validation framework that can be used to generate comprehensible explanations with ILP on top of the relevance output of GNN explainers and human-expected relevance for concepts learned by GNNs. Our experiments conducted on our benchmark data set demonstrate that it is possible to extract symbolic concepts from the most relevant explanations that are representative of what a GNN has learned. Our findings open up a variety of avenues for future research on validatable explanations for GNNs.
{"title":"Generating Explanations for Conceptual Validation of Graph Neural Networks: An Investigation of Symbolic Predicates Learned on Relevance-Ranked Sub-Graphs.","authors":"Bettina Finzel, Anna Saranti, Alessa Angerschmid, David Tafler, Bastian Pfeifer, Andreas Holzinger","doi":"10.1007/s13218-022-00781-7","DOIUrl":"https://doi.org/10.1007/s13218-022-00781-7","url":null,"abstract":"<p><p>Graph Neural Networks (GNN) show good performance in relational data classification. However, their contribution to concept learning and the validation of their output from an application domain's and user's perspective have not been thoroughly studied. We argue that combining symbolic learning methods, such as Inductive Logic Programming (ILP), with statistical machine learning methods, especially GNNs, is an essential forward-looking step to perform powerful and validatable relational concept learning. In this contribution, we introduce a benchmark for the conceptual validation of GNN classification outputs. It consists of the symbolic representations of symmetric and non-symmetric figures that are taken from a well-known Kandinsky Pattern data set. We further provide a novel validation framework that can be used to generate comprehensible explanations with ILP on top of the relevance output of GNN explainers and human-expected relevance for concepts learned by GNNs. Our experiments conducted on our benchmark data set demonstrate that it is possible to extract symbolic concepts from the most relevant explanations that are representative of what a GNN has learned. Our findings open up a variety of avenues for future research on validatable explanations for GNNs.</p>","PeriodicalId":45413,"journal":{"name":"Kunstliche Intelligenz","volume":"36 3-4","pages":"271-285"},"PeriodicalIF":2.9,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9794543/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10817409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号