Unsupervised Learning Based On Artificial Neural Network: A Review

Artificial neural networks (ANN) have been applied effectively in numerous fields for the aim of prediction, knowledge discovery, classification, time series analysis, modeling, etc. ANN training can be assorted into Supervised learning, Reinforcement learning and Unsupervised learning. There are some limitations using supervised learning. These limitations can be overcome by using unsupervised learning technique. This gives us motivation to write a review on unsupervised learning based on ANN. One main problem associated with unsupervised learning is how to find the hidden structures in unlabeled data. This paper reviews on the training/learning of unsupervised learning based on artificial neural network. It provides a description of the methods of selecting and fixing a number of hidden nodes in an unsupervised learning environment based on ANN. Moreover, the status, benefits and challenges of unsupervised learning are also summarized.

[1]  Hao Yu,et al.  Selection of Proper Neural Network Sizes and Architectures—A Comparative Study , 2012, IEEE Transactions on Industrial Informatics.

[2]  Mrudang D. Pandya,et al.  A Survey: Artificial Neural Network for Character Recognition , 2015, SocProS.

[3]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[4]  N. Shilbayeh,et al.  Role of Hidden Neurons in an Elman Recurrent Neural Network in Classification of Cavitation Signals , 2020 .

[5]  Jian Pei,et al.  Data Mining: Concepts and Techniques, 3rd edition , 2006 .

[6]  M. Torma,et al.  Kohonen self-organizing feature map and its use in clustering , 1994, Other Conferences.

[7]  Yusman Yusof,et al.  Utilizing unsupervised weightless neural network as autonomous states classifier in reinforcement learning algorithm , 2017, 2017 IEEE 13th International Colloquium on Signal Processing & its Applications (CSPA).

[8]  W. Singer,et al.  Selection of intrinsic horizontal connections in the visual cortex by correlated neuronal activity. , 1992, Science.

[9]  Sridha Sridharan,et al.  Improving deep convolutional neural networks with unsupervised feature learning , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[10]  Kenneth D. Bailey,et al.  Numerical Taxonomy and Cluster Analysis , 1994 .

[11]  Mahesh Panchal,et al.  Review on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network , 2014 .

[12]  Deok-Hwan Kim,et al.  Solving local minima problem with large number of hidden nodes on two-layered feed-forward artificial neural networks , 2008, Neurocomputing.

[13]  S. Karsoliya,et al.  Approximating Number of Hidden layer neurons in Multiple Hidden Layer BPNN Architecture , 2012 .

[14]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[15]  Björn Ommer,et al.  Self-Supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[16]  I. Tomek.  An Experiment with the Edited Nearest-Neighbor Rule , 1976 .

[17]  S. Sumathi,et al.  Introduction to neural networks using MATLAB 6.0 , 2006 .

[18]  Marco Wiering,et al.  Reinforcement Learning and Markov Decision Processes , 2012, Reinforcement Learning.

[19]  Jiawei Han,et al.  Data Mining: Concepts and Techniques, Second Edition , 2006, The Morgan Kaufmann series in data management systems.

[20]  Victoria J. Hodge,et al.  A Survey of Outlier Detection Methodologies , 2004, Artificial Intelligence Review.

[21]  Sheela Rani.B.  Role of Hidden Neurons in an Elman Recurrent Neural Network in Classification of Cavitation Signals , 2012 .

[22]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[23]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[24]  R. Asadi,et al.  An unsupervised feed forward neural network method for efficient clustering , 2017, Int. Arab J. Inf. Technol..

[25]  Ameet Talwalkar,et al.  Foundations of Machine Learning , 2012, Adaptive computation and machine learning.

[26]  Bart Baesens,et al.  A new SOM-based method for profile generation: Theory and an application in direct marketing , 2012, Eur. J. Oper. Res..

[27]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[28]  Demetrios G. Sampson,et al.  Building Adaptive Tutoring Model Using Artificial Neural Networks and Reinforcement Learning , 2017, 2017 IEEE 17th International Conference on Advanced Learning Technologies (ICALT).

[30]  Geoffrey E. Hinton.  Deep belief networks , 2009, Scholarpedia.

[31]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[32]  Cheng-Yuan Liou,et al.  Modeling word perception using the Elman network , 2008, Neurocomputing.

[33]  Zhen Ma,et al.  A review of algorithms for medical image segmentation and their applications to the female pelvic cavity , 2010, Computer methods in biomechanics and biomedical engineering.