Big Data Deep Learning: Challenges and Perspectives

By Xue-wen Chen, Xiaotong Lin. 2014

1,175 citations recorded by the source corpus.

Deep learning is currently an extremely active research area in machine learning and pattern recognition society. It has gained huge successes in a broad area of applications such as speech recognition, computer vision, and natural language processing. With the sheer size of data available today, big data brings big opportunities and transformative potential for various sectors; on the other hand, it also presents unprecedented challenges to harnessing data and information. As the data keeps getting bigger, deep learning is coming to play a key role in providing big data predictive analytics solutions. In this paper, we provide a brief overview of deep learning, and highlight current research efforts and the challenges to big data, as well as the future trends.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Haibo He
2. Chunyan Miao
3. Ding Wang
4. Omer Berat Sezer
5. Dusist Niyato
6. Qiang Yang
7. Derong Liu
8. Ala Al-Fuqaha

Citations in the corpus

• Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, background): “Running DL on distributed frameworks or clusters of CPUs with parallel processing is a viable solution that has been developed [7].”
• The role of big data analytics in Internet of Things (2017, background): “Deep learning [57], machine learning [58], and artificial intelligence [59] are key technologies that provide value added applications using IoT and big data.”
• Flow of Information in Feed-Forward Deep Neural Networks (2016, background): “Due to their fascinating performance, different deep learning structures have been deployed in various applications in the past decades [1], [2], [3].”
• A Survey on Deep Learning in Big Data (2017, background): “-Heterogeneity: refers to different types of data such as structured, unstructured and semi-structured [11].”
• Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker (2016, background): “Several different network architectures have been proposed, which have enabled to reach state-of-the-art predictive performance in many computer vision and speech recognition tasks (Chen and Lin, 2014; Deng and Yu, 2013).”
• Adaptive Critic Nonlinear Robust Control: A Survey (2017, background): “2712188 intelligence techniques such as machine learning [1], [2] and deep learning [3]–[5] are extremely helpful for the study of big data [6], [7].”
• Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture (2019, background): “With increased processing power and continuous developments in graphics processors, DL has the potential to improve prediction tasks as the computational burden reduces significantly [4].”
• A Review on Applications of Computational Methods in Drug Screening and Design (2020, methodology): “Just when the molecular descriptors are not selected, the deep learning method will automatically select representations from original data and high-dimensional data [88] .”
• Multiscale Kernel Based Residual Convolutional Neural Network for Motor Fault Diagnosis Under Nonstationary Conditions (2020, neutral): “Therefore, traditional fault diagnosis methods have been re-examined from the point of big data [12], [13].”
• Deep Computation Model for Unsupervised Feature Learning on Big Data (2016, methodology): “Index Terms—Big data, deep learning model, tensor auto-encoder, back-propagation algorithm, feature learning Ç”
• A survey towards an integration of big data analytics to big insights for value-creation (2018, background): “9 describes the big data storage for various platforms (Hu et al., 2014; Chen, 2014).”
• A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends (2018, background): “Deep learning has shown significant potential in approximating and reducing large, complex datasets into highly accurate predictive and transformational output, greatly facilitating human-centered smart systems [25], [98].”
• Molecular Docking: Shifting Paradigms in Drug Discovery (2019, background): “Finally, GPU computing made big data-driven computation tasks accessible to a larger public [201], and it is expected to play a prominent role, not only in docking but in future in silico drug design in general [202].”
• A Survey on Internet of Things From Industrial Market Perspective (2015, background): “Sensory data produced by a single sensor will not provide the necessary information that can be used to fully understand the situation [32].”