发布求助
文献互助 智能选刊 最新文献

LatinX in AI at International Conference on Machine Learning 2021最新文献

筛选
英文 中文
Long Short-Term Memory with Slower Information Decay 具有较慢信息衰减的长短期记忆
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2022-12-14 DOI: 10.52591/2021072418
H. Chien, Javier Turek, Nicole M. Beckage, Vy A. Vo, C. Honey, Ted L. Willke
{"title":"Long Short-Term Memory with Slower Information Decay","authors":"H. Chien, Javier Turek, Nicole M. Beckage, Vy A. Vo, C. Honey, Ted L. Willke","doi":"10.52591/2021072418","DOIUrl":"https://doi.org/10.52591/2021072418","url":null,"abstract":"Learning to process long-range dependencies has been a challenge for recurrent neural networks. Despite improvements achieved by long shortterm memory (LSTMs), its gating mechanism results in exponential decay of information, limiting their capacity of capturing long-range dependencies. In this work, we present a power law forget gate, which instead has a slower rate of information decay. We propose a power law-based LSTM (pLSTM) based on the LSTM but with a power law forget gate. We test empirically the pLSTM on the copy task, sentiment classification, and sequential MNIST, all with long-range dependency tasks. The pLSTM solves these tasks outperforming an LSTM, specially for long-range dependencies. Further, the pLSTM learns sparser and more robust representations.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115066658","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}
引用次数: 0
GAN-based Data Mapping for Model Adaptation 基于gan的模型自适应数据映射
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2022-12-14 DOI: 10.52591/2021072415
Felipe Leno da Silva, R. Glatt, Raphael Cóbe, R. Vicente
{"title":"GAN-based Data Mapping for Model Adaptation","authors":"Felipe Leno da Silva, R. Glatt, Raphael Cóbe, R. Vicente","doi":"10.52591/2021072415","DOIUrl":"https://doi.org/10.52591/2021072415","url":null,"abstract":"Although Machine Learning algorithms are solving tasks of ever-increasing complexity, gathering data and building training sets remains an error prone, costly, and difficult problem. However, reusing knowledge from related previouslysolved tasks enables reducing the amount of data required to learn a new task. We here propose a method for learning a mapping model that maps data from a source task with labeled data to a related target task with only unlabeled data. We perform an empirical evaluation showing that our method achieves performance comparable to a model learned directly in the target task.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126804195","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}
引用次数: 0
Community pooling: LDA topic modeling in Twitter 社区池:Twitter中的LDA主题建模
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2022-12-14 DOI: 10.52591/2021072417
F. Albanese, E. Feuerstein
{"title":"Community pooling: LDA topic modeling in Twitter","authors":"F. Albanese, E. Feuerstein","doi":"10.52591/2021072417","DOIUrl":"https://doi.org/10.52591/2021072417","url":null,"abstract":"Social networks play a fundamental role in propagation of information and news. Characterizing the content of the messages becomes vital for tasks like fake news detection or personalized message recommendation. However, Twitter posts are short and often less coherent than other text documents, which makes it challenging to apply text mining algorithms efficiently. We propose a new pooling scheme for topic modeling in Twitter, which groups tweets whose authors belong to the same community on the retweet network into a single document. Our findings contribute to an improved methodology for identifying the latent topics in a Twitter dataset, without modifying the basic machinery of a topic decomposition model. In particular, we used Latent Dirichlet Allocation (LDA) and empirically showed that this novel method achieves better results than previous pooling methods in terms of cluster quality, document retrieval tasks, supervised machine learning classification and overall run time.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129771249","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}
引用次数: 0
A Tree-Adaptation Mechanism for Covariate and Concept Drift 协变量和概念漂移的树适应机制
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2022-12-14 DOI: 10.52591/2021072414
Felipe Leno da Silva, Raphael Cóbe, R. Vicente
{"title":"A Tree-Adaptation Mechanism for Covariate and Concept Drift","authors":"Felipe Leno da Silva, Raphael Cóbe, R. Vicente","doi":"10.52591/2021072414","DOIUrl":"https://doi.org/10.52591/2021072414","url":null,"abstract":"Although Machine Learning algorithms are solving tasks of ever-increasing complexity, gathering data and building training sets remains an error prone, costly, and difficult problem. However, reusing knowledge from related previouslysolved tasks enables reducing the amount of data required to learn a new task. We here propose a method for reusing a tree-based model learned in a source task with abundant data in a target task with scarce data. We perform an empirical evaluation showing that our method is useful, especially in scenarios where the labels are unavailable in the target task.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121239996","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}
引用次数: 0
Anticipating faults by predicting non-linearity of environment variables with neural networks: a case study in semiconductor manufacturing 利用神经网络预测环境变量的非线性来预测故障:以半导体制造为例
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2022-12-14 DOI: 10.52591/2021072419
Mateus Begnini Melchiades, Lincoln Vinicius Schreiber, Gabriel de Oliveira Ramos, Cesar David Paredes Crovato, Rodrigo Ivan Goytia Mejia, Rodrigo da Rosa Righi
{"title":"Anticipating faults by predicting non-linearity of environment variables with neural networks: a case study in semiconductor manufacturing","authors":"Mateus Begnini Melchiades, Lincoln Vinicius Schreiber, Gabriel de Oliveira Ramos, Cesar David Paredes Crovato, Rodrigo Ivan Goytia Mejia, Rodrigo da Rosa Righi","doi":"10.52591/2021072419","DOIUrl":"https://doi.org/10.52591/2021072419","url":null,"abstract":"The present work proposes a neural network model capable of anticipating possible faults in a semiconductor manufacturing plant by predicting non-linearity spikes in sensor data. Early detection of significant variation can be crucial for identifying machinery degradation or issues in the process itself. We use non-linearity as it is not affected by regular process changes and autocorrelation, thus avoiding false-positives in the neural network caused by changes in demand and the presence of control systems. The developed model is able to predict up to 30min of future non-linearity with loss ≤ 0.5. Furthermore, the proposed model is flexible enough to present itself as a starting point for future work in the field of fault detection in other areas.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123753839","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}
引用次数: 0
Generalized linear tree: a flexible algorithm for predicting continuous variables 广义线性树:一种预测连续变量的灵活算法
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2022-12-14 DOI: 10.52591/2021072420
Alberto Rodrigues Ferreira, Alex Akira Okuno
{"title":"Generalized linear tree: a flexible algorithm for predicting continuous variables","authors":"Alberto Rodrigues Ferreira, Alex Akira Okuno","doi":"10.52591/2021072420","DOIUrl":"https://doi.org/10.52591/2021072420","url":null,"abstract":"Tree-based models are popular among regression methods to predict continuous variables. Also, Generalized Linear Models (GLMs) are pretty standard in many statistical applications and provide a generalization to many of the most commonly applied statistical procedures. However, in most regression tree methods, there is only one theoretical model associated for prediction in the final nodes, like multiple linear regression, logistic regressions, polynomial models, Poisson models, among others. We, therefore, propose a new tree method in which we estimate a GLM in each leaf node of the estimated tree including variable selection, new hyperparameters optimization, and tree pruning. Our method, called Generalized linear tree (GLT), has shown to be competitive compared to other well-known regression methods in real datasets, with the advantages and estimation flexibility provided by GLMs.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130885005","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}
引用次数: 0
Mask-net: Detection of Correct Use of Masks Through Computer Vision Mask-net:通过计算机视觉检测口罩的正确使用
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2022-12-14 DOI: 10.52591/2021072416
Alexander Kalen Targa, Alberto Landi Cortiñas, Nicolas Araque Volk, Alejandro Marcano Van Grieken
{"title":"Mask-net: Detection of Correct Use of Masks Through Computer Vision","authors":"Alexander Kalen Targa, Alberto Landi Cortiñas, Nicolas Araque Volk, Alejandro Marcano Van Grieken","doi":"10.52591/2021072416","DOIUrl":"https://doi.org/10.52591/2021072416","url":null,"abstract":"This paper focuses on creating a system for recognizing the correct use of a mask through computer vision techniques. Research was carried out with aims of establishing the criteria for the creation of custom datasets, which were used to train, validate and test a pair of deep learning models, Mask-net and I-Mask-net. Both were designed with similar architectures, making use of Transfer Learning Techniques. The results given by training showed that the fine tuning carried out was adequate, while the tests carried out showed that the models have an acceptable level of accuracy, reaching 85.47% for Mask-net and 85.96% for IMask-net, additionally supported by the obtained precision, recall and F1-Score calculations.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126202029","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}
引用次数: 1
Sparse Data Generation for Particle-Based Simulation of Hadronic Jets in the LHC 大型强子对撞机中基于粒子的强子射流模拟稀疏数据生成
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2021-07-24 DOI: 10.52591/202107246
B. Orzari, T. Tomei, M. Pierini, M. Touranakou, Javier Mauricio Duarte, R. Kansal, J. Vlimant, D. Gunopulos
{"title":"Sparse Data Generation for Particle-Based Simulation of Hadronic Jets in the LHC","authors":"B. Orzari, T. Tomei, M. Pierini, M. Touranakou, Javier Mauricio Duarte, R. Kansal, J. Vlimant, D. Gunopulos","doi":"10.52591/202107246","DOIUrl":"https://doi.org/10.52591/202107246","url":null,"abstract":"We develop a generative neural network for the generation of sparse data in particle physics using a permutation-invariant and physics-informed loss function. The input dataset used in this study consists of the particle constituents of hadronic jets due to its sparsity and the possibility of evaluating the network’s ability to accurately describe the particles and jets properties. A variational autoencoder composed of convolutional layers in the encoder and decoder is used as the generator. The loss function consists of a reconstruction error term and the Kullback-Leibler divergence between the output of the encoder and the latent vector variables. The permutation-invariant loss on the particles’ properties is combined with two mean-squared error terms that measure the difference between input and output jets mass and transverse momentum, which improves the network’s generation capability as it imposes physics constraints, allowing the model to learn the kinematics of the jets.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116086948","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}
引用次数: 7
Convolutional Neural Networks Evaluation for COVID-19 Classification on Chest Radiographs 卷积神经网络在胸片COVID-19分类中的应用
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2021-07-24 DOI: 10.52591/lxai2021072412
F. Zeiser, C. D. da Costa, Gabriel Ss de Oliveira
{"title":"Convolutional Neural Networks Evaluation for COVID-19 Classification on Chest Radiographs","authors":"F. Zeiser, C. D. da Costa, Gabriel Ss de Oliveira","doi":"10.52591/lxai2021072412","DOIUrl":"https://doi.org/10.52591/lxai2021072412","url":null,"abstract":"Early identification of patients with COVID-19 is essential to enable adequate treatment and to reduce the burden on the health system. The gold standard for COVID-19 detection is the use of RT-PCR tests. However, due to the high demand for tests, these can take days or even weeks in some regions of Brazil. Thus, an alternative for the detection of COVID-19 is the analysis of Chest X-rays (CXR). This paper proposes the evaluation of convolutional neural networks to identify pneumonia due to COVID-19 in CXR. The proposed methodology consists of an evaluation of six convolutional architectures pre-trained with the ImageNet dataset: InceptionResNetV2, InceptionV3, MovileNetV2, ResNet50, VGG16, and Xception. The obtained results for our methodology demonstrate that the Xception architecture presented a superior performance in the classification of CXR, with an Accuracy of 85.64%, Sensitivity of 85.71%, Specificity of 85.65%, F1-score of 85.49%, and an AUC of 0.9648.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127490455","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}
引用次数: 1
Population Dynamics for Discrete Wasserstein Gradient Flows over Networks 网络上离散Wasserstein梯度流的种群动力学
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2021-07-24 DOI: 10.52591/202107241
Gilberto Díaz-García, César A. Uribe, N. Quijano
{"title":"Population Dynamics for Discrete Wasserstein Gradient Flows over Networks","authors":"Gilberto Díaz-García, César A. Uribe, N. Quijano","doi":"10.52591/202107241","DOIUrl":"https://doi.org/10.52591/202107241","url":null,"abstract":"We study the problem of minimizing a convex function over probability measures supported in a graph. We build upon the recent formulation of optimal transport over discrete domains to propose a method that generates a sequence that provably converges to a minimum of the objective function and smoothly transports mass over the edges of the graph. Moreover, we identify novel relation between Riemannian gradient flows and perturbed best response protocols that provide sufficient conditions for the convergence of the proposed algorithm. Numerical results show practical advantages over existing approaches with respect to the implementability and convergence rates.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115008615","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}
引用次数: 0
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信