2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)最新文献_第2页

Asynchronous Multitask Reinforcement Learning with Dropout for Continuous Control 基于Dropout的异步多任务连续控制强化学习

2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) Pub Date : 2019-12-01 DOI: 10.1109/ICMLA.2019.00099

Z. Jiao, J. Oh

{"title":"Asynchronous Multitask Reinforcement Learning with Dropout for Continuous Control","authors":"Z. Jiao, J. Oh","doi":"10.1109/ICMLA.2019.00099","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00099","url":null,"abstract":"Deep reinforcement learning is sample inefficient for solving complex tasks. Recently, multitask reinforcement learning has received increased attention because of its ability to learn general policies with improved sample efficiency. In multitask reinforcement learning, a single agent must learn multiple related tasks, either sequentially or simultaneously. Based on the DDPG algorithm, this paper presents Asyn-DDPG, which asynchronously learns a multitask policy for continuous control with simultaneous worker agents. We empirically found that sparse policy gradients can significantly reduce interference among conflicting tasks and make multitask learning more stable and sample efficient. To ensure the sparsity of gradients evaluated for each task, Asyn-DDPG represents both actor and critic functions as deep neural networks and regularizes them using Dropout. During training, worker agents share the actor and the critic functions, and asynchronously optimize them using task-specific gradients. For evaluating Asyn-DDPG, we proposed robotic navigation tasks based on realistically simulated robots and physics-enabled maze-like environments. Although the number of tasks used in our experiment is small, each task is conducted based on a real-world setting and posts a challenging environment. Through extensive evaluation, we demonstrate that Dropout regularization can effectively stabilize asynchronous learning and enable Asyn-DDPG to outperform DDPG significantly. Also, Asyn-DDPG was able to learn a multitask policy that can be well generalized for handling environments unseen during training.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122864083","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: 3

Bayesian Topological Learning for Brain State Classification 脑状态分类的贝叶斯拓扑学习

2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) Pub Date : 2019-12-01 DOI: 10.1109/ICMLA.2019.00205

Farzana Nasrin, Christopher Oballe, D. Boothe, V. Maroulas

引用次数: 11

Feature Changes in Source Code for Commit Classification Into Maintenance Activities 在源代码中对提交分类进行维护活动的特性更改

2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) Pub Date : 2019-12-01 DOI: 10.1109/ICMLA.2019.00096

R. Mariano, G. E. D. Santos, Markos V. de Almeida, Wladmir Cardoso Brandão

引用次数: 11

Complete Rare Event Specification using Stochastic Treatment: CRESST 使用随机处理完成罕见事件规范:CRESST

2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) Pub Date : 2019-12-01 DOI: 10.1109/ICMLA.2019.00131

Debanjan Banerjee, Ritish Menon

引用次数: 0

Unsupervised Topic Model Based Text Network Construction for Learning Word Embeddings 基于无监督主题模型的文本网络构建及其词嵌入学习

2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) Pub Date : 2019-12-01 DOI: 10.1109/ICMLA.2019.00032

S. Chung, Michael D'Arcy

{"title":"Unsupervised Topic Model Based Text Network Construction for Learning Word Embeddings","authors":"S. Chung, Michael D'Arcy","doi":"10.1109/ICMLA.2019.00032","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00032","url":null,"abstract":"Distributed word embeddings have proven remarkably effective at capturing word level semantic and syntactic regularities in language for many natural language processing tasks. One recently proposed semi-supervised representation learning method called Predictive Text Embedding (PTE) utilizes both semantically labeled and unlabeled data in information networks to learn the embedding of text that produces state of-the-art performance when compared to other embedding methods. However, PTE uses supervised label information to construct one of the networks and many other possible ways of constructing such information networks are left untested. We present two unsupervised methods that can be used in constructing a large scale semantic information network from documents by combining topic models that have emerged as a powerful technique of finding useful structure in an unstructured text collection as it learns distributions over words. The first method uses Latent Dirichlet Allocation (LDA) to build a topic model over text, and constructs a word topic network with edge weights proportional to the word-topic probability distributions. The second method trains an unsupervised neural network to learn the word-document distribution, with a single hidden layer representing a topic distribution. The two weight matrices of the neural net are directly reinterpreted as the edge weights of heterogeneous text networks that can be used to train word embeddings to build an effective low dimensional representation that preserves the semantic closeness of words and documents for NLP tasks. We conduct extensive experiments to evaluate the effectiveness of our methods.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129234792","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

Text Classification via Network Topology: A Case Study on the Holy Quran 基于网络拓扑的文本分类——以《古兰经》为例

2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) Pub Date : 2019-12-01 DOI: 10.1109/ICMLA.2019.00257

M. E. Aktas, Esra Akbas

引用次数: 4

Anomaly Dataset Augmentation Using the Sequence Generative Models 使用序列生成模型的异常数据集增强

2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) Pub Date : 2019-12-01 DOI: 10.1109/ICMLA.2019.00190

Sunguk Shin, Inseop Lee, Changhee Choi

引用次数: 6

Predictive and Prescriptive Analytics for Performance Optimization: Framework and a Case Study on a Large-Scale Enterprise System 性能优化的预测和规范分析:大型企业系统的框架和案例研究

2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) Pub Date : 2019-12-01 DOI: 10.1109/ICMLA.2019.00152

I. John, R. Karumanchi, S. Bhatnagar

{"title":"Predictive and Prescriptive Analytics for Performance Optimization: Framework and a Case Study on a Large-Scale Enterprise System","authors":"I. John, R. Karumanchi, S. Bhatnagar","doi":"10.1109/ICMLA.2019.00152","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00152","url":null,"abstract":"In any industrial or software system, predicting future values of measurable parameters well in advance is of utmost importance for avoiding disruptions. The historical data on system parameters measured at regular time intervals can be leveraged to address this long horizon prediction problem. However, complex interdependencies between the parameters and the need for avoiding false recommendations pose challenges in this prediction task. An equally challenging and useful exercise is to identify the 'important' parameters and optimize them in order to attain good system performance. This paper describes a generic framework, along with specific methods, for this data analytics problem and presents a case study on a large-scale enterprise system. The proposed method combines techniques from machine learning, causal analysis, time-series analysis and stochastic optimization to achieve accurate prediction (estimating future values of parameters) and reliable prescription (controlling independent parameters to optimize system performance). The approach is validated with data from a large-scale enterprise service bus consisting of about 30 parameters measured at 5 minute intervals over a period of 6 months.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116478204","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

Colorectal Polyp Segmentation by U-Net with Dilation Convolution 基于扩张卷积的U-Net结肠息肉分割

2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) Pub Date : 2019-12-01 DOI: 10.1109/ICMLA.2019.00148

Xinzi Sun, Pengfei Zhang, Dechun Wang, Yu Cao, Benyuan Liu

{"title":"Colorectal Polyp Segmentation by U-Net with Dilation Convolution","authors":"Xinzi Sun, Pengfei Zhang, Dechun Wang, Yu Cao, Benyuan Liu","doi":"10.1109/ICMLA.2019.00148","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00148","url":null,"abstract":"Colorectal cancer (CRC) is one of the most commonly diagnosed cancers and a leading cause of cancer deaths in the United States. Colorectal polyps that grow on the intima of the colon or rectum is an important precursor for CRC. Currently, the most common way for colorectal polyp detection and precancerous pathology is the colonoscopy. Therefore, accurate colorectal polyp segmentation during the colonoscopy procedure has great clinical significance in CRC early detection and prevention. In this paper, we propose a novel end-to-end deep learning framework for the colorectal polyp segmentation. The model we design consists of an encoder to extract multi-scale semantic features and a decoder to expand the feature maps to a polyp segmentation map. We improve the feature representation ability of the encoder by introducing the dilated convolution to learn high-level semantic features without resolution reduction. We further design a simplified decoder which combines multi-scale semantic features with fewer parameters than the traditional architecture. Furthermore, we apply three post processing techniques on the output segmentation map to improve colorectal polyp detection performance. Our method achieves state-of-the-art results on CVC-ClinicDB and ETIS-Larib Polyp DB.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121471257","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: 53

Understanding Cohesion in Writings and Speech of Schizophrenia Patients 理解精神分裂症患者写作和言语中的衔接

2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) Pub Date : 2019-12-01 DOI: 10.1109/ICMLA.2019.00068

Amal AlQahtani, Efsun Sarioglu Kayi, Mona T. Diab

引用次数: 1