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
Image Inpainting Applied to Art Completing Escher’s Print Gallery 图像绘画应用于艺术完成埃舍尔的版画画廊
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2021-07-24 DOI: 10.52591/lxai202107247
Lucia Cip, Simone Caenazzo, Gaston Mazzei, Aditya Srinivas
{"title":"Image Inpainting Applied to Art Completing Escher’s Print Gallery","authors":"Lucia Cip, Simone Caenazzo, Gaston Mazzei, Aditya Srinivas","doi":"10.52591/lxai202107247","DOIUrl":"https://doi.org/10.52591/lxai202107247","url":null,"abstract":"This extended abstract presents the first stages of a research in inpainting suited for art reconstruction. We introduce M.C Escher’s Print Gallery lithography as a use-case example. This artwork presents a void on its center and additionally, it follows a challenging mathematical structure that needs to be preserved by the inpainting method. We present our work so far and our future line of research.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"30 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":"133947709","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 : 2021-07-24 DOI: 10.52591/lxai2021072420
A. Okuno, Alberto Ferreira
{"title":"Generalized linear tree: a flexible algorithm for predicting continuous variables","authors":"A. Okuno, Alberto Ferreira","doi":"10.52591/lxai2021072420","DOIUrl":"https://doi.org/10.52591/lxai2021072420","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":"28 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":"122134934","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
Computation of Discrete Flows Over Networks via Constrained Wasserstein Barycenters 基于约束Wasserstein重心的网络离散流计算
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2021-07-24 DOI: 10.52591/202107244
Barycenters, Ferran Arqué, César A. Uribe, C. Ocampo‐Martinez
{"title":"Computation of Discrete Flows Over Networks via Constrained Wasserstein Barycenters","authors":"Barycenters, Ferran Arqué, César A. Uribe, C. Ocampo‐Martinez","doi":"10.52591/202107244","DOIUrl":"https://doi.org/10.52591/202107244","url":null,"abstract":"We study a Wasserstein attraction approach for solving dynamic mass transport problems over networks. In the transport problem over networks, we start with a distribution over the set of nodes that needs to be “transported” to a target distribution accounting for the network topology. We exploit the specific structure of the problem, characterized by the computation of implicit gradient steps, and formulate an approach based on discretized flows. As a result, our proposed algorithm relies on the iterative computation of constrained Wasserstein barycenters. We show how the proposed method finds approximate solutions to the network transport problem, taking into account the topology of the network, the capacity of the communication channels, and the capacity of the individual nodes.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"34 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":"123827718","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
Aspect-based Sentiment Analysis using BERT with Disentangled Attention 基于方面的注意力解纠缠BERT情感分析
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2021-07-24 DOI: 10.52591/lxai2021072410
R. Marcacini, Emanuel Silva
{"title":"Aspect-based Sentiment Analysis using BERT with Disentangled Attention","authors":"R. Marcacini, Emanuel Silva","doi":"10.52591/lxai2021072410","DOIUrl":"https://doi.org/10.52591/lxai2021072410","url":null,"abstract":"Aspect-Based Sentiment Analysis (ABSA) tasks aim to identify consumers’ opinions about different aspects of products or services. BERT-based language models have been used successfully in applications that require a deep understanding of the language, such as sentiment analysis. This paper investigates the use of disentangled learning to improve BERT-based textual representations in ABSA tasks. Motivated by the success of disentangled representation learning in the field of computer vision, which aims to obtain explanatory factors of the data representations, we explored the recent DeBERTa model (Decoding-enhanced BERT with Disentangled Attention) to disentangle the syntactic and semantics features from a BERT architecture. Experimental results show that incorporating disentangled attention and a simple fine-tuning strategy for downstream tasks outperforms state-of-the-art models in ABSA’s benchmark datasets.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"3 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":"126974093","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: 12
A multiple strategy for plant species identification using images of leaf texture 基于叶片纹理图像的植物物种识别策略研究
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2021-07-24 DOI: 10.52591/202107243
Nubia Rosa, Igor Luidji, Sérgio F Da Silva, Douglas Farias
{"title":"A multiple strategy for plant species identification using images of leaf texture","authors":"Nubia Rosa, Igor Luidji, Sérgio F Da Silva, Douglas Farias","doi":"10.52591/202107243","DOIUrl":"https://doi.org/10.52591/202107243","url":null,"abstract":"In our planet there are thousands of plant species, being important to catalog these to help in the biodiversity preservation. However, identifying various plant species is not an easy task, even for specialists. Methods of computer vision for identifying plant species are interesting solutions for these difficulties. This work aims to analyze the efficiency of texture feature extraction methods applied in the identification of plant species by means of images of its leaves. For this, different texture descriptors were applied in three different databases. The obtained results indicate that local phase quantization (LPQ)-based methods achieve great efficiency and robustness. Additionally, the combination of LPQ-based methods with a segmentation based fractal texture analysis (SFTA) has increased the correct classification rate in all databases.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"39 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":"132006850","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
Towards Explainable Deep Reinforcement Learning for Traffic Signal Control 面向交通信号控制的可解释深度强化学习
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2021-07-24 DOI: 10.52591/lxai202107249
Lincoln V. Schreiber, G. Ramos, A. Bazzan
{"title":"Towards Explainable Deep Reinforcement Learning for Traffic Signal Control","authors":"Lincoln V. Schreiber, G. Ramos, A. Bazzan","doi":"10.52591/lxai202107249","DOIUrl":"https://doi.org/10.52591/lxai202107249","url":null,"abstract":"Deep reinforcement learning has shown potential for traffic signal control. However, the lack of explainability has limited its use in real-world conditions. In this work, we present a Deep Q-learning approach, with the SHAP framework, able to explain its policy. Our approach can explain the impact of features on each action, which promotes the understanding of how the agent behaves in the face of different traffic conditions. Furthermore, our approach improved travel time, waiting time, and speed by 21.49%, 27.97%, 20.87%, compared to fixed-time traffic signal controllers.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"125 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":"132627906","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: 2
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 : 2021-07-24 DOI: 10.52591/lxai2021072415
M. Melchiades, L. Schreiber, G. Ramos, C. Paredes, Rodrigo Goytia, Rodrigo da Rosa
{"title":"Anticipating faults by predicting non-linearity of environment variables with neural networks: a case study in semiconductor manufacturing","authors":"M. Melchiades, L. Schreiber, G. Ramos, C. Paredes, Rodrigo Goytia, Rodrigo da Rosa","doi":"10.52591/lxai2021072415","DOIUrl":"https://doi.org/10.52591/lxai2021072415","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":"79 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":"123999848","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
Spatial Attention Adapted to a LSTM Architecture with Frame Selection for Human Action Recognition in Videos 基于LSTM框架的视频人体动作识别
LatinX in AI at International Conference on Machine Learning 2021 Pub Date : 2021-07-24 DOI: 10.52591/lxai2021072411
Carlos Ismael Orozco, M. Buemi, J. J. Berlles
{"title":"Spatial Attention Adapted to a LSTM Architecture with Frame Selection for Human Action Recognition in Videos","authors":"Carlos Ismael Orozco, M. Buemi, J. J. Berlles","doi":"10.52591/lxai2021072411","DOIUrl":"https://doi.org/10.52591/lxai2021072411","url":null,"abstract":"Action recognition in videos is currently a topic of interest in the area of computer vision, due to potential applications such as: multimedia indexing, surveillance in public spaces, among others. In this work we propose an attention mechanism adapted to a CNN–LSTM base architecture. To carry out the training and testing phases, we used the HMDB-51 and UCF-101 datasets. We evaluate the performance of our system using accuracy as the evaluation metric, obtaining 57.3% and 90.4% for HMDB-51 and UCF-101 respectively.","PeriodicalId":196347,"journal":{"name":"LatinX in AI at International Conference on Machine Learning 2021","volume":"101 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":"116665188","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
首页 上一页
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