5,154 Hits in 4.2 sec

An overview of multi-task learning

Yu Zhang, Qiang Yang
2017 National Science Review  
Then several different settings of MTL are introduced, including multi-task supervised learning, multi-task unsupervised learning, multi-task semi-supervised learning, multi-task active learning, multi-task  ...  reinforcement learning, multi-task online learning and multi-task multi-view learning.  ...  such as convolutional neural networks and recurrent neural networks.  ... 
doi:10.1093/nsr/nwx105 fatcat:7w67kng7ufbandtcneeniropny

Speech Recognition Using Deep Neural Networks: a Systematic Review

Ali Bou Nassif, Ismail Shahin, Imtinan Attili, Mohammad Azzeh, Khaled Shaalan.
2019 IEEE Access  
INDEX TERMS Speech recognition, deep neural network, systematic review.  ...  This paper provides a thorough examination of the different studies that have been conducted since 2006, when deep learning first arose as a new area of machine learning, for speech applications.  ...  Five main techniques of machine learning exist which are: supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning and finally deep learning.  ... 
doi:10.1109/access.2019.2896880 fatcat:6lpbl2uwbvfh3blahxtbxicka4

Diabetes Disease Prediction Using Machine Learning

Preetha S, Chandan N, Darshan N K, Gowrav P B.
2020 International Journal of Recent Trends in Engineering and Research  
Data mining is known as the process of sorting through a large number of data sets to create relationships and to find patterns for solving a given problem through data analysis.  ...  A variety of tests would be expected from the patient to diagnose a certain disease. However, using the data mining technique, the number of tests can be minimized.  ...  INTRODUCTION Machine learning can be divided into four forms, Un-supervised learning; Supervised learning; Semi-supervised learning; and Reinforcement learning.  ... 
doi:10.23883/ijrter.2020.6029.65q5h fatcat:x52pjn2ybjcpflqqx4auiy6xma


Dr. Yojna Arora
2020 International Journal of Innovative Research in Computer Science & Technology  
Machine Learning Algorithms can be categorized as Supervised, Unsupervised, Semi Supervised and Reinforcement [12] Supervised Learning algorithms apply the predefined knowledge on the new set of data  ...  inferences.Semi Supervised Learning Algorithm is a combination of both Supervised and Unsupervised Learning.  ... 
doi:10.21276/ijircst.2020.8.3.34 fatcat:jtlm3l7g7nan5oilx42wlgqxlq

Machine Learning for Reliability Engineering and Safety Applications: Review of Current Status and Future Opportunities [article]

Zhaoyi Xu, Joseph Homer Saleh
2020 arXiv   pre-print
There is already a large but fragmented literature on ML for reliability and safety applications, and it can be overwhelming to navigate and integrate into a coherent whole.  ...  We then look back and review the use of ML in reliability and safety applications.  ...  Semi-supervised learning applications Semi-supervised learning algorithms are used in fault detection and identification, in prognostics and RUL prediction, which are important for maintenance planning  ... 
arXiv:2008.08221v1 fatcat:qhbkiepabfaz7afhctqutncheq


Jaseena K.U.
2018 International Journal of Advanced Research in Computer Science  
Deep learning is appropriate for exploiting large volumes of data and for analysing raw data from multiple sources and in different styles.  ...  The large volumes of data collected by organizations are utilized for various purposes such as for solving problems in marketing, technology, medical science, national intelligence, fraud detection etc  ...  Figure 2 . 2 Unsupervised learning Figure 3 . 3 Semi-supervised learning Feed forward neural networks and Recurrent Neural Networks are variants of Deep Neural Networks.  ... 
doi:10.26483/ijarcs.v9i1.5136 fatcat:3oniwqwp4fbzzkicxozhn3ms5y

A review of various semi-supervised learning models with a deep learning and memory approach

Jamshid Bagherzadeh, Hasan Asil
2018 Iran Journal of Computer Science  
A research solution for future studies is to benefit from memory to increase such an effect. Memory-based neural networks are new models of neural networks which can be used in this area.  ...  In addition, deep neural networks are used to extract data features using a multilayer model.  ...  Learning problems are divided into four groups: supervised, unsupervised, semi-supervised, and reinforcement [3] .  ... 
doi:10.1007/s42044-018-00027-6 fatcat:nccifurxyzc33fa5xfprrlupxq

A Review of Unsupervised Artificial Neural Networks with Applications

Samson Damilola
2019 International Journal of Computer Applications  
Artificial Neural Networks (ANNs) are models formulated to mimic the learning capability of human brains. Learning in ANNs can be categorized into supervised, reinforcement and unsupervised learning.  ...  Application of supervised ANNs is limited to when the supervisor's knowledge of the environment is sufficient to supply the networks with labelled datasets.  ...  In supervised learning, as its name implies, the artificial neural network is under the supervision of a teacher (say, a system designer) who uses his or her knowledge of the environment to train the network  ... 
doi:10.5120/ijca2019918425 fatcat:v3u4m3d24bdflkq7vryiya66mu

Artificial intelligence and chimeric antigen receptor T-cell therapy

Lidia Gil, Maksymilian Grajek
2022 Acta Haematologica Polonica  
This article has been peer reviewed and published immediately upon acceptance.  ...  (Declaration of Helsinki) for experiments involving humans; EU Directive 2010/63/EU for animal experiments; uniform requirements for manuscripts submitted to biomedical journals.  ...  Financial support The authors declare no financial support for this work Ethics The work described in this article has been carried out in accordance with The Code of Ethics of the World Medical Association  ... 
doi:10.5603/ahp.a2022.0019 fatcat:z6cxgj2brzerzg4gh3ljy5obmu

How Do Machines Learn? Artificial Intelligence as a New Era in Medicine

Oliwia Koteluk, Adrian Wartecki, Sylwia Mazurek, Iga Kołodziejczak, Andrzej Mackiewicz
2021 Journal of Personalized Medicine  
With an increased number of medical data generated every day, there is a strong need for reliable, automated evaluation tools.  ...  This review explains different models and the general process of machine learning and training the algorithms.  ...  Acknowledgments: We would like to thank Poznan University of Medical Sciences (Poznan, Poland) and Greater Poland Cancer Centre (Poznan, Poland) for supporting this work.  ... 
doi:10.3390/jpm11010032 pmid:33430240 fatcat:ghkitfkujvh7djnma7gtkx5w3i

Machine Learning (ML) in Medicine: Review, Applications, and Challenges

Amir Masoud Rahmani, Efat Yousefpoor, Mohammad Sadegh Yousefpoor, Zahid Mehmood, Amir Haider, Mehdi Hosseinzadeh, Rizwan Ali Naqvi
2021 Mathematics  
learning, semi-supervised learning, and reinforcement learning), evaluation methods (simulation-based evaluation and practical implementation-based evaluation in real environment) and applications (diagnosis  ...  According to our proposed classification, we review some studies presented in machine learning applications for healthcare.  ...  Institutional Review Board Statement: Not applicable. Informed Consent Statement: Not applicable. Data Availability Statement: Not applicable.  ... 
doi:10.3390/math9222970 fatcat:rkdhwxlw4zhsxbtoayzaxoqmwu

Using Artificial Intelligence for Space Challenges: A Survey

Antonia Russo, Gianluca Lax
2022 Applied Sciences  
Moreover, we present and discuss current solutions proposed for each challenge to allow researchers to identify and compare the state of the art in this context.  ...  Still, recently, the space sector is a field where artificial intelligence is receiving significant attention.  ...  Institutional Review Board Statement: Not applicable. Informed Consent Statement: Not applicable.  ... 
doi:10.3390/app12105106 fatcat:jlkdbe4panbqfhridpozon6634

Feature Evaluation of Emerging E-Learning Systems Using Machine Learning: An Extensive Survey

Shabnam Mohamed Aslam, Abdul Khader Jilani, Jabeen Sultana, Laila Almutairi
2021 IEEE Access  
The motivation behind this research analysis is to separate the potential outcomes of assessing e-learning models utilizing AI strategies such as Supervised, Semi Supervised, Reinforced Learning advances  ...  E-learning issues are a standard examination issue for us all.  ...  SEMI SUPERVISED MACHINE LEARNING ALGORITHMS Semi-supervised learning methods are suitable for elearning problems of known input parameters and unknown output parameters.  ... 
doi:10.1109/access.2021.3077663 fatcat:avwqkzxvufauvjjyebbm3twnpe

Detecting Deceptive Reviews using Generative Adversarial Networks [article]

Hojjat Aghakhani, Aravind Machiry, Shirin Nilizadeh, Christopher Kruegel, Giovanni Vigna
2018 arXiv   pre-print
While FakeGAN is built upon a semi-supervised classifier, known for less accuracy, our evaluation results on a dataset of TripAdvisor hotel reviews show the same performance in terms of accuracy as of  ...  With the successful use of Neural Networks on various classification applications, in this paper, we propose FakeGAN a system that for the first time augments and adopts Generative Adversarial Networks  ...  ACKNOWLEDGEMENTS We would like to thank the anonymous reviewers for their valuable comments.  ... 
arXiv:1805.10364v1 fatcat:ovditq2povbjnjtyedmoht4lsm

A Review of Identity Methods of Internet of Things (IOT)

Sana Abdelaziz Bkheet, Johnson I. Agbinya
2021 Advances in Internet of Things  
The paper discusses the existing identification methods for IOT. Moreover, it provides a review of the modern identification methods proposed in recent literature.  ...  IOT can collect, process, and exchange data via a data communication network.  ...  , unsupervised, semi supervised and reinforcement as shown in Figure 3 .  ... 
doi:10.4236/ait.2021.114011 fatcat:id36gm72qzem7dsy4woggfgrb4
« Previous Showing results 1 — 15 out of 5,154 results