Filters








124 Hits in 4.9 sec

Autonomous Deep Learning: Incremental Learning of Denoising Autoencoder for Evolving Data Streams [article]

Mahardhika Pratama, Andri Ashfahani, Yew Soon Ong, Savitha Ramasamy, Edwin Lughofer
2018 arXiv   pre-print
An automated construction of a denoising autoeconder, namely deep evolving denoising autoencoder (DEVDAN), is proposed in this paper.  ...  The generative learning phase of Autoencoder (AE) and its successor Denosing Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabelled samples.  ...  A deep evolving denoising autoencoder (DEVDAN) for evolving data streams is proposed in this paper.  ... 
arXiv:1809.09081v1 fatcat:ted6lpslajdbvpjmyqfpqhitly

Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments [article]

Andri Ashfahani, Mahardhika Pratama
2019 arXiv   pre-print
The feasibility of deep neural networks (DNNs) to address data stream problems still requires intensive study because of the static and offline nature of conventional deep learning approaches.  ...  A deep continual learning algorithm, namely autonomous deep learning (ADL), is proposed in this paper.  ...  Incremental learning of denoising autoencoder (DAE) realizes the structural learning mechanism via the network's loss and the hidden unit merging mechanism [29] .  ... 
arXiv:1810.07348v2 fatcat:5eavov7icnagdmbgzhaf7k3x2a

Online deep learning based on auto-encoder

Si-si Zhang, Jian-wei Liu, Xin Zuo, Run-kun Lu, Si-ming Lian
2021 Applied intelligence (Boston)  
is not suitable for modeling streaming data with evolving probability distribution.  ...  Online learning is an important technical means for sketching massive real-time and high-speed data.  ...  Lughofer, Autonomous deep learn- ing: Incremental learning of denoising autoencoder for evolving data streams, arXiv preprint arXiv:1809.09081 (2018).  ... 
doi:10.1007/s10489-020-02058-8 fatcat:wmuyx4ed6fhptispjnpa7ssvpu

Unsupervised Continual Learning in Streaming Environments [article]

Andri Ashfahani, Mahardhika Pratama
2021 arXiv   pre-print
While automatic construction of the deep networks in streaming environments remains an open issue, it is also hindered by the expensive labeling cost of data streams rendering the increasing demand for  ...  A deep clustering network is desired for data streams because of its aptitude in extracting natural features thus bypassing the laborious feature engineering step.  ...  In [16] , it makes use of the incremental learning of denoising autoencoder coupled with the hashing algorithm.  ... 
arXiv:2109.09282v1 fatcat:giicorsetbhvheitv4hoqu7efm

Learning to Navigate by Growing Deep Networks [article]

Thushan Ganegedara, Lionel Ott, Fabio Ramos
2017 arXiv   pre-print
In this paper, we present a self-supervised framework for robots to learn to navigate, without any prior knowledge of the environment, by incrementally building the structure of a deep network as new data  ...  The deep architecture, named Reinforced Adaptive Denoising Autoencoders (RA-DAE), uses reinforcement learning to dynamically change the network structure by adding or removing neurons.  ...  Reinforced Adaptive Denoising Autoencoder (RA-DAE) [Ganegedara et al., 2016] is a deep learning technique that uses reinforcement learning to dynamically adapt the structure of a deep network as the  ... 
arXiv:1712.05084v1 fatcat:p6r75kxkendd5otglhmeinrnwy

A Review of Machine Learning and Deep Learning Techniques for Anomaly Detection in IoT Data

Redhwan Al-amri, Raja Kumar Murugesan, Mustafa Man, Alaa Fareed Abdulateef, Mohammed A. Al-Sharafi, Ammar Ahmed Alkahtani
2021 Applied Sciences  
Research challenges related to data evolving, feature-evolving, windowing, ensemble approaches, nature of input data, data complexity and noise, parameters selection, data visualizations, heterogeneity  ...  The nature of data, anomaly types, learning mode, window model, datasets, and evaluation criteria are also presented.  ...  Conflicts of Interest: The authors have no conflict of interest.  ... 
doi:10.3390/app11125320 fatcat:cjbzetn3xbb3tlm7lebaglujei

Continual Lifelong Learning with Neural Networks: A Review [article]

German I. Parisi, Ronald Kemker, Jose L. Part, Christopher Kanan, Stefan Wermter
2019 arXiv   pre-print
Consequently, lifelong learning capabilities are crucial for autonomous agents interacting in the real world and processing continuous streams of information.  ...  This limitation represents a major drawback for state-of-the-art deep neural network models that typically learn representations from stationary batches of training data, thus without accounting for situations  ...  The authors would like to thank Sascha Griffiths, Vincenzo Lomonaco, Sebastian Risi, and Jun Tani for valuable feedback and suggestions.  ... 
arXiv:1802.07569v3 fatcat:6zn2hqi2djbu3lx5mbr75nvipq

2021 Index IEEE Transactions on Neural Networks and Learning Systems Vol. 32

2021 IEEE Transactions on Neural Networks and Learning Systems  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  July 2021 3262-3267 Deep Residual Autoencoders for Expectation Maximization-Inspired Dictio-nary Learning.  ... 
doi:10.1109/tnnls.2021.3134132 fatcat:2e7comcq2fhrziselptjubwjme

Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges [article]

Muhammad Usama, Junaid Qadir, Aunn Raza, Hunain Arif, Kok-Lim Alvin Yau, Yehia Elkhatib, Amir Hussain, Ala Al-Fuqaha
2017 arXiv   pre-print
control (e.g., for developing autonomous self-driving cars).  ...  We provide a comprehensive survey highlighting the recent advancements in unsupervised learning techniques and describe their applications for various learning tasks in the context of networking.  ...  Finally, denoising autoencoders are used to learn the mapping of a corrupted data point to its original location in the data space in unsupervised manner for manifold learning and reconstruction distribution  ... 
arXiv:1709.06599v1 fatcat:llcg6gxgpjahha6bkhsitglrsm

Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges

Muhammad Usama, Junaid Qadir, Aunn Raza, Hunain Arif, Kok-lim Alvin Yau, Yehia Elkhatib, Amir Hussain, Ala Al-Fuqaha
2019 IEEE Access  
and optimal control (e.g., for developing autonomous self-driving cars).  ...  In addition, unsupervised learning can unconstrain us from the need for labeled data and manual handcrafted feature engineering, thereby facilitating flexible, general, and automated methods of machine  ...  Finally, denoising autoencoders are used to learn the mapping of a corrupted data point to its original location in the data space in an unsupervised manner for manifold learning and reconstruction distribution  ... 
doi:10.1109/access.2019.2916648 fatcat:xutxh3neynh4bgcsmugxsclkna

Deep Learning-Based Security Behaviour Analysis in IoT Environments: A Survey

Yawei Yue, Shancang Li, Phil Legg, Fuzhong Li, Honghao Gao
2021 Security and Communication Networks  
This paper aims to provide a thorough survey related to deep learning applications in IoT for security and privacy concerns. Our primary focus is on deep learning enhanced IoT security.  ...  Second, from the security perspective of IoT systems, we analyse the suitability of deep learning to improve security. Finally, we evaluate the performance of deep learning in IoT system security.  ...  Consequently, lifelong learning capabilities are crucial for computational learning systems and autonomous agents interacting in the real world and processing continuous streams of information.  ... 
doi:10.1155/2021/8873195 fatcat:oh4dcicpsfdcvmkfn5z2lgr2lm

Online Semisupervised Learning Approach for Quality Monitoring of Complex Manufacturing Process

Weng Weiwei, Mahardhika Pratama, Andri Ashfahani, Edward Yapp Kien Yee, Taeseong Kim
2021 Complexity  
ParsNet++ features the one-pass learning approach to deal with streaming data while characterizing elastic structure to overcome rapidly changing data distributions.  ...  in the quality monitoring because it calls for full supervision in labelling data samples.  ...  Acknowledgments is project was financially supported by National Research Foundation, Republic of Singapore, under IAFPP in the AME domain (contract no. A19C1A0018).  ... 
doi:10.1155/2021/3005276 fatcat:yydiqsdn3fchtl7csuntqc7mzu

A trans-disciplinary review of deep learning research and its relevance for water resources scientists

Chaopeng Shen
2018 Water Resources Research  
Deep learning (DL), a new-generation of artificial neural network research, has transformed industries, daily lives and various scientific disciplines in recent years.  ...  DL is especially suited for information extraction from image-like data and sequential data. Techniques and experiences presented in other disciplines are of high relevance to water research.  ...  Autoencoders and stacked denoising autoencoders (SDAEs) Autoencoders (Ballard, 1987; Hinton & Salakhutdinov, 2006) are important structural elements for deep networks.  ... 
doi:10.1029/2018wr022643 fatcat:ruopsnchg5eg5hsiccyadinf54

Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Survey [article]

Xun Chen, Chang Li, Aiping Liu, Martin J. McKeown, Ruobing Qian, Z. Jane Wang
2021 arXiv   pre-print
In recent years, deep learning (DL) has emerged as a potential solution for such problems due to its superior capacity in feature extraction.  ...  Combining DL with domain-specific knowledge may allow for development of robust approaches to decode brain activity even with small-sample data.  ...  Her research interests include statistical signal processing and machine learning, with applications in digital media and biomedical data analytics.  ... 
arXiv:2112.06654v2 fatcat:roxf5k7ypfcvtdzz3pbho3kdri

A review of Federated Learning in Intrusion Detection Systems for IoT [article]

Aitor Belenguer, Javier Navaridas, Jose A. Pascual
2022 arXiv   pre-print
Intrusion detection systems are evolving into intelligent systems that perform data analysis searching for anomalies in their environment.  ...  The development of deep learning technologies opened the door to build more complex and effective threat detection models.  ...  Javier Navaridas is a Ramón y Cajal fellow from the Spanish Ministry of Science, Innovation and Universities (RYC2018-024829-I).  ... 
arXiv:2204.12443v2 fatcat:eodordo7b5hwpim4qpvr3dxhm4
« Previous Showing results 1 — 15 out of 124 results