Pub Date : 2024-03-25DOI: 10.1007/978-3-031-45368-7_15
Antônio Carlos Souza Ferreira Júnior, Thiago Alves Rocha
{"title":"An Incremental MaxSAT-Based Model to Learn Interpretable and Balanced Classification Rules","authors":"Antônio Carlos Souza Ferreira Júnior, Thiago Alves Rocha","doi":"10.1007/978-3-031-45368-7_15","DOIUrl":"https://doi.org/10.1007/978-3-031-45368-7_15","url":null,"abstract":"","PeriodicalId":335206,"journal":{"name":"Brazilian Conference on Intelligent Systems","volume":" 52","pages":"227-242"},"PeriodicalIF":0.0,"publicationDate":"2024-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140384944","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 : 2024-03-24DOI: 10.1007/978-3-031-45368-7_10
Francisco Mateus Rocha, Thiago Alves Rocha, Reginaldo Pereira Fernandes Ribeiro, A. Neto
{"title":"Logic-Based Explanations for Linear Support Vector Classifiers with Reject Option","authors":"Francisco Mateus Rocha, Thiago Alves Rocha, Reginaldo Pereira Fernandes Ribeiro, A. Neto","doi":"10.1007/978-3-031-45368-7_10","DOIUrl":"https://doi.org/10.1007/978-3-031-45368-7_10","url":null,"abstract":"","PeriodicalId":335206,"journal":{"name":"Brazilian Conference on Intelligent Systems","volume":" 7","pages":"144-159"},"PeriodicalIF":0.0,"publicationDate":"2024-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140385725","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 : 2023-05-03DOI: 10.1007/978-3-031-21689-3_17
Guilherme O. Ribeiro, Alexandre Soli Soares, J. T. Carvalho, M. Grellert
{"title":"Event Detection in Therapy Sessions for Children with Autism","authors":"Guilherme O. Ribeiro, Alexandre Soli Soares, J. T. Carvalho, M. Grellert","doi":"10.1007/978-3-031-21689-3_17","DOIUrl":"https://doi.org/10.1007/978-3-031-21689-3_17","url":null,"abstract":"","PeriodicalId":335206,"journal":{"name":"Brazilian Conference on Intelligent Systems","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132936379","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 : 2023-01-18DOI: 10.1007/978-3-031-21689-3_28
M. Mathias, Wesley P. de Almeida, Jefferson F. Coelho, L. P. Freitas, F. M. Moreno, Caio F. D. Netto, F. G. Cozman, A. H. R. Costa, E. Tannuri, E. Gomi, M. Dottori
{"title":"Augmenting a Physics-Informed Neural Network for the 2D Burgers Equation by Addition of Solution Data Points","authors":"M. Mathias, Wesley P. de Almeida, Jefferson F. Coelho, L. P. Freitas, F. M. Moreno, Caio F. D. Netto, F. G. Cozman, A. H. R. Costa, E. Tannuri, E. Gomi, M. Dottori","doi":"10.1007/978-3-031-21689-3_28","DOIUrl":"https://doi.org/10.1007/978-3-031-21689-3_28","url":null,"abstract":"","PeriodicalId":335206,"journal":{"name":"Brazilian Conference on Intelligent Systems","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128847343","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 : 2022-10-06DOI: 10.48550/arXiv.2210.03743
George Correa de Ara'ujo, H. Pedrini
Single image super-resolution (SISR) is the process of obtaining one high-resolution version of a low-resolution image by increasing the number of pixels per unit area. This method has been actively investigated by the research community, due to the wide variety of real-world problems where it can be applied, from aerial and satellite imaging to compressed image and video enhancement. Despite the improvements achieved by deep learning in the field, the vast majority of the used networks are based on traditional convolutions, with the solutions focusing on going deeper and/or wider, and innovations coming from jointly employing successful concepts from other fields. In this work, we decided to step up from the traditional convolutions and adopt the concept of capsules. Since their overwhelming results both in image classification and segmentation problems, we question how suitable they are for SISR. We also verify that different solutions share most of their configurations, and argue that this trend leads to fewer explorations of network varieties. During our experiments, we check various strategies to improve results, ranging from new and different loss functions to changes in the capsule layers. Our network achieved good results with fewer convolutional-based layers, showing that capsules might be a concept worth applying in the image super-resolution problem.
{"title":"Single Image Super-Resolution Based on Capsule Neural Networks","authors":"George Correa de Ara'ujo, H. Pedrini","doi":"10.48550/arXiv.2210.03743","DOIUrl":"https://doi.org/10.48550/arXiv.2210.03743","url":null,"abstract":"Single image super-resolution (SISR) is the process of obtaining one high-resolution version of a low-resolution image by increasing the number of pixels per unit area. This method has been actively investigated by the research community, due to the wide variety of real-world problems where it can be applied, from aerial and satellite imaging to compressed image and video enhancement. Despite the improvements achieved by deep learning in the field, the vast majority of the used networks are based on traditional convolutions, with the solutions focusing on going deeper and/or wider, and innovations coming from jointly employing successful concepts from other fields. In this work, we decided to step up from the traditional convolutions and adopt the concept of capsules. Since their overwhelming results both in image classification and segmentation problems, we question how suitable they are for SISR. We also verify that different solutions share most of their configurations, and argue that this trend leads to fewer explorations of network varieties. During our experiments, we check various strategies to improve results, ranging from new and different loss functions to changes in the capsule layers. Our network achieved good results with fewer convolutional-based layers, showing that capsules might be a concept worth applying in the image super-resolution problem.","PeriodicalId":335206,"journal":{"name":"Brazilian Conference on Intelligent Systems","volume":"159 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115162109","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 : 2022-10-04DOI: 10.48550/arXiv.2210.01638
Lucas F. F. Cardoso, Joseph Ribeiro, Vitor Santos, Raíssa Silva, M. Mota, R. Prudêncio, Ronnie Alves
, Abstract. Intelligent systems that use Machine Learning classification algorithms are increasingly common in everyday society. However, many systems use black-box models that do not have characteristics that allow for self-explanation of their predictions. This situation leads researchers in the field and society to the following question: How can I trust the prediction of a model I cannot understand? In this sense, XAI emerges as a field of AI that aims to create techniques capable of explaining the decisions of the classifier to the end-user. As a result, several techniques have emerged, such as Explanation-by-Example, which has a few initia-tives consolidated by the community currently working with XAI. This research explores the Item Response Theory (IRT) as a tool to explaining the models and measuring the level of reliability of the Explanation-by-Example approach. To this end, four datasets with different levels of complexity were used, and the Random Forest model was used as a hy-pothesis test. From the test set, 83.8% of the errors are from instances in which the IRT points out the model as unreliable. Learning (ML) · Item Response Theory (IRT) · Classification.
{"title":"Explanation-by-Example Based on Item Response Theory","authors":"Lucas F. F. Cardoso, Joseph Ribeiro, Vitor Santos, Raíssa Silva, M. Mota, R. Prudêncio, Ronnie Alves","doi":"10.48550/arXiv.2210.01638","DOIUrl":"https://doi.org/10.48550/arXiv.2210.01638","url":null,"abstract":", Abstract. Intelligent systems that use Machine Learning classification algorithms are increasingly common in everyday society. However, many systems use black-box models that do not have characteristics that allow for self-explanation of their predictions. This situation leads researchers in the field and society to the following question: How can I trust the prediction of a model I cannot understand? In this sense, XAI emerges as a field of AI that aims to create techniques capable of explaining the decisions of the classifier to the end-user. As a result, several techniques have emerged, such as Explanation-by-Example, which has a few initia-tives consolidated by the community currently working with XAI. This research explores the Item Response Theory (IRT) as a tool to explaining the models and measuring the level of reliability of the Explanation-by-Example approach. To this end, four datasets with different levels of complexity were used, and the Random Forest model was used as a hy-pothesis test. From the test set, 83.8% of the errors are from instances in which the IRT points out the model as unreliable. Learning (ML) · Item Response Theory (IRT) · Classification.","PeriodicalId":335206,"journal":{"name":"Brazilian Conference on Intelligent Systems","volume":"974 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132519058","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 : 2022-09-06DOI: 10.48550/arXiv.2209.02456
Wington L. Vital, Guilherme Vieira, M. E. Valle
The universal approximation theorem asserts that a single hidden layer neural network approximates continuous functions with any desired precision on compact sets. As an existential result, the universal approximation theorem supports the use of neural networks for various applications, including regression and classification tasks. The universal approximation theorem is not limited to real-valued neural networks but also holds for complex, quaternion, tessarines, and Clifford-valued neural networks. This paper extends the universal approximation theorem for a broad class of hypercomplex-valued neural networks. Precisely, we first introduce the concept of non-degenerate hypercomplex algebra. Complex numbers, quaternions, and tessarines are examples of non-degenerate hypercomplex algebras. Then, we state the universal approximation theorem for hypercomplex-valued neural networks defined on a non-degenerate algebra.
{"title":"Extending the Universal Approximation Theorem for a Broad Class of Hypercomplex-Valued Neural Networks","authors":"Wington L. Vital, Guilherme Vieira, M. E. Valle","doi":"10.48550/arXiv.2209.02456","DOIUrl":"https://doi.org/10.48550/arXiv.2209.02456","url":null,"abstract":"The universal approximation theorem asserts that a single hidden layer neural network approximates continuous functions with any desired precision on compact sets. As an existential result, the universal approximation theorem supports the use of neural networks for various applications, including regression and classification tasks. The universal approximation theorem is not limited to real-valued neural networks but also holds for complex, quaternion, tessarines, and Clifford-valued neural networks. This paper extends the universal approximation theorem for a broad class of hypercomplex-valued neural networks. Precisely, we first introduce the concept of non-degenerate hypercomplex algebra. Complex numbers, quaternions, and tessarines are examples of non-degenerate hypercomplex algebras. Then, we state the universal approximation theorem for hypercomplex-valued neural networks defined on a non-degenerate algebra.","PeriodicalId":335206,"journal":{"name":"Brazilian Conference on Intelligent Systems","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114085104","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 : 2022-01-10DOI: 10.1007/978-3-030-91702-9_34
B. Afonso, Lilian Berton
{"title":"Optimizing Diffusion Rate and Label Reliability in a Graph-Based Semi-supervised Classifier","authors":"B. Afonso, Lilian Berton","doi":"10.1007/978-3-030-91702-9_34","DOIUrl":"https://doi.org/10.1007/978-3-030-91702-9_34","url":null,"abstract":"","PeriodicalId":335206,"journal":{"name":"Brazilian Conference on Intelligent Systems","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128560651","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 : 2021-11-04DOI: 10.1007/978-3-030-91699-2_14
Joao P. A. Dantas, André N. Costa, Diego Geraldo, M. Maximo, T. Yoneyama
{"title":"Weapon Engagement Zone Maximum Launch Range Estimation Using a Deep Neural Network","authors":"Joao P. A. Dantas, André N. Costa, Diego Geraldo, M. Maximo, T. Yoneyama","doi":"10.1007/978-3-030-91699-2_14","DOIUrl":"https://doi.org/10.1007/978-3-030-91699-2_14","url":null,"abstract":"","PeriodicalId":335206,"journal":{"name":"Brazilian Conference on Intelligent Systems","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131784462","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 : 2021-10-19DOI: 10.1007/978-3-030-91699-2_29
F. N. Caccao, M. M. Jos'e, A. Oliveira, Stefano Spindola, A. H. R. Costa, Fabio Gagliardi Cozman
{"title":"DEEPAGÉ: Answering Questions in Portuguese about the Brazilian Environment","authors":"F. N. Caccao, M. M. Jos'e, A. Oliveira, Stefano Spindola, A. H. R. Costa, Fabio Gagliardi Cozman","doi":"10.1007/978-3-030-91699-2_29","DOIUrl":"https://doi.org/10.1007/978-3-030-91699-2_29","url":null,"abstract":"","PeriodicalId":335206,"journal":{"name":"Brazilian Conference on Intelligent Systems","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117317907","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：