Výsledky vyhľadávania - "Computing methodologies Machine learning"

On-the-fly Improving Performance of Deep Code Models via Input Denoising Autor Tian, Zhao, Chen, Junjie, Zhang, Xiangyu

“…Deep learning has been widely adopted to tackle various code-based tasks by building deep code models based on a large amount of code snippets. While these…”
Získať plný text

Detecting and Explaining Anomalies Caused by Web Tamper Attacks via Building Consistency-based Normality Autor Liao, Yifan, Xu, Ming, Lin, Yun, Teoh, Xiwen, Xie, Xiaofei, Feng, Ruitao, Liauw, Frank, Zhang, Hongyu, Dong, Jin Song

“…Web applications are crucial infrastructures in the modern society, which have high demand of reliability and security. However, their frontend can be…”
Získať plný text

SLIM: a Scalable and Interpretable Light-weight Fault Localization Algorithm for Imbalanced Data in Microservice Autor Ren, Rui, Yang, Jingbang, Yang, Linxiao, Gu, Xinyue, Sun, Liang

“… This paper proposes a novel method that utilizes decision rule sets to deal with highly imbalanced data by optimizing the F1 score subject to cardinality constraints…”
Získať plný text

GANtlitz: Ultra High Resolution Generative Model for Multi‐Modal Face Textures Autor Gruber, A., Collins, E., Meka, A., Mueller, F., Sarkar, K., Orts‐Escolano, S., Prasso, L., Busch, J., Gross, M., Beeler, T.

“… The acquisition of high resolution assets at scale is cumbersome, it involves enrolling a large number of human subjects, using expensive multi…”
Získať plný text

The Art and Practice of Data Science Pipelines: A Comprehensive Study of Data Science Pipelines In Theory, In-The-Small, and In-The-Large Autor Biswas, Sumon, Wardat, Mohammad, Rajan, Hridesh

“…Increasingly larger number of software systems today are including data science components for descriptive, predictive, and prescriptive analytics. The…”
Získať plný text

Multilingual training for Software Engineering Autor Ahmed, Toufique, Devanbu, Premkumar

“… Several SE tasks have all been subject to this approach, with performance gradually improving over the past several years with better models and training methods…”
Získať plný text

Prioritizing Test Inputs for Deep Neural Networks via Mutation Analysis Autor Wang, Zan, You, Hanmo, Chen, Junjie, Zhang, Yingyi, Dong, Xuyuan, Zhang, Wenbin

“…Deep Neural Network (DNN) testing is one of the most widely-used ways to guarantee the quality of DNNs. However, labeling test inputs to check the correctness…”
Získať plný text

Safe DNN-type Controller Synthesis for Nonlinear Systems via Meta Reinforcement Learning Autor Zhao, Hanrui, Zeng, Xia, Qi, Niuniu, Yang, Zhengfeng, Zeng, Zhenbing

“…) controllers for nonlinear systems subject to safety constraints. Our approach incorporates two phases…”
Získať plný text

Operation is the Hardest Teacher: Estimating DNN Accuracy Looking for Mispredictions Autor Guerriero, Antonio, Pietrantuono, Roberto, Russo, Stefano

“…Deep Neural Networks (DNN) are typically tested for accuracy relying on a set of unlabelled real world data (operational dataset), from which a subset is…”
Získať plný text

Exploring Classifiers with Differentiable Decision Boundary Maps Autor Machado, A., Behrisch, M., Telea, A.

“…Explaining Machine Learning (ML) — and especially Deep Learning (DL) — classifiers' decisions is a subject of interest across fields due to the increasing ubiquity of such models in computing systems…”
Získať plný text

How to Support ML End-User Programmers through a Conversational Agent Autor Garcia, Emily Arteaga, Pimentel, Joao Felipe, Feng, Zixuan, Gerosa, Marco, Steinmacher, Igor, Sarma, Anita

“… them. To evaluate the efficacy of Newton's design, we conducted a Wizard of Oz within-subjects study with 12 ML-EUPs…”
Získať plný text

Enhancing Deep Reinforcement Learning with Executable Specifications Autor Yerushalmi, Raz

“…Deep reinforcement learning (DRL) has become a dominant paradigm for using deep learning to carry out tasks where complex policies are learned for reactive…”
Získať plný text

AaceGEN: Attention Guided Adversarial Code Example Generation for Deep Code Models Autor Li, Zhong, Zhang, Chong, Pan, Minxue, Zhang, Tian, Li, Xuandong

“…Adversarial code examples are important to investigate the robustness of deep code models. Existing work on adversarial code example generation has shown…”
Získať plný text

Automatic Extraction of Cause-Effect-Relations from Requirements Artifacts Autor Frattini, Julian, Junker, Maximilian, Unterkalmsteiner, Michael, Mendez, Daniel

“…) causal sentences convey essential context about the subject of requirements, and (3) extracted and formalized causality relations are usable for a (semi…”
Získať plný text

Personalization without user interruption: boosting activity recognition in new subjects using unlabeled data Autor Fallahzadeh, Ramin, Ghasemzadeh, Hassan

“… In this paper, we propose an uninformed cross-subject transfer learning algorithm that leverages the cross-user similarities by constructing a network-based feature-level representation of the data…”
Získať plný text

Accurate Body Pose Matching for Individuals with Stroke using Siamese Networks Autor Gokhman, Ruslan, Sawdayi, Talya, Khan, Rana, Satyanarayana, Ashwin, Vinjamuri, Ramana, Kadiyala, Sai Praveen

“…Stroke is one of the major causes of long-term disability in United States. With more than 800,00 people experiencing stroke every year, it is important that efficient means for recovery are presented to support stroke subjects…”
Získať plný text

Convolutional Neural Networks for Biomedical Text Classification: Application in Indexing Biomedical Articles Autor Rios, Anthony, Kavuluru, Ramakanth

“…) outperforms several traditional approaches in biomedical text classification with the specific use-case of assigning medical subject headings (or MeSH terms…”
Zistit podrobnosti o prístupe

Efficient Model Learning from Joint-Action Demonstrations for Human-Robot Collaborative Tasks Autor Nikolaidis, Stefanos, Ramakrishnan, Ramya, Keren Gu, Shah, Julie

“…We present a framework for automatically learning human user models from joint-action demonstrations that enables a robot to compute a robust policy for a…”
Získať plný text

Towards robust activity recognition for everyday life: Methods and evaluation Autor Reiss, Attila, Stricker, Didier, Hendeby, Gustaf

“… Two important aspects of robustness are investigated: dealing with various (unknown) other activities and subject independency…”
Získať plný text

GraphConfRec: A Graph Neural Network-Based Conference Recommender System Autor Iana, Andreea, Paulheim, Heiko

“…In today's academic publishing model, especially in Computer Science, conferences commonly constitute the main platforms for releasing the latest peer-reviewed…”
Získať plný text