Unsupervised Learning Based On Artificial Neural Network: A Review
Citations Over TimeTop 10% of 2018 papers
Abstract
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.
Related Papers
- → Semi-supervised learning: a brief review(2018)232 cited
- → Semi-supervised Learning(2020)30 cited
- → TWSVM for Unsupervised and Semi-supervised Learning(2016)4 cited
- → Controlled Competitive Learning: Extending Competitive Learning to Supervised Learning(2007)
- Supervised Competition Using Joined Growing Neural Gas(2014)