Deep learning applications and challenges in big data analytics

MM Najafabadi, F Villanustre, TM Khoshgoftaar… - Journal of big …, 2015 - Springer
Abstract Big Data Analytics and Deep Learning are two high-focus of data science. Big Data
has become important as many organizations both public and private have been collecting …

Selecting influential examples: Active learning with expected model output changes

A Freytag, E Rodner, J Denzler - … September 6-12, 2014, Proceedings, Part …, 2014 - Springer
In this paper, we introduce a new general strategy for active learning. The key idea of our
approach is to measure the expected change of model outputs, a concept that generalizes …

A benchmark and comparison of active learning for logistic regression

Y Yang, M Loog - Pattern Recognition, 2018 - Elsevier
Logistic regression is by far the most widely used classifier in real-world applications. In this
paper, we benchmark the state-of-the-art active learning methods for logistic regression and …

Nonparametric part transfer for fine-grained recognition

C Goring, E Rodner, A Freytag… - Proceedings of the …, 2014 - openaccess.thecvf.com
In the following paper, we present an approach for fine-grained recognition based on a new
part detection method. In particular, we propose a nonparametric label transfer technique …

Batch mode active learning for regression with expected model change

W Cai, M Zhang, Y Zhang - IEEE transactions on neural …, 2016 - ieeexplore.ieee.org
While active learning (AL) has been widely studied for classification problems, limited efforts
have been done on AL for regression. In this paper, we introduce a new AL framework for …

Using big data to improve the performance management: a case study from the UAE FM industry

M Mawed, A Al-Hajj - Facilities, 2017 - emerald.com
Purpose This paper aims to explore how big data analytics (BDA) collected and stored
through specific data software [Construction Operations Building Information Exchange …

Knowledge augmented machine learning with applications in autonomous driving: A survey

J Wörmann, D Bogdoll, C Brunner, E Bührle… - arXiv preprint arXiv …, 2022 - arxiv.org
The availability of representative datasets is an essential prerequisite for many successful
artificial intelligence and machine learning models. However, in real life applications these …

Active learning and discovery of object categories in the presence of unnameable instances

C Kading, A Freytag, E Rodner… - Proceedings of the …, 2015 - openaccess.thecvf.com
Current visual recognition algorithms are" hungry" for data but massive annotation is
extremely costly. Therefore, active learning algorithms are required that reduce labeling …

Change detection using high resolution remote sensing images based on active learning and Markov random fields

H Yu, W Yang, G Hua, H Ru, P Huang - Remote Sensing, 2017 - mdpi.com
Change detection has been widely used in remote sensing, such as for disaster assessment
and urban expansion detection. Although it is convenient to use unsupervised methods to …

Optimised probabilistic active learning (OPAL) for fast, non-myopic, cost-sensitive active classification

G Krempl, D Kottke, V Lemaire - Machine Learning, 2015 - Springer
In contrast to ever increasing volumes of automatically generated data, human annotation
capacities remain limited. Thus, fast active learning approaches that allow the efficient …