Analysis of recent advancement in unsupervised deep learning

Abstract

Deep Learning (DL) has experienced considerable reach and success in the number of various application areas in recent years. The modern era of Machine learning has been rapidly developing and extended to most Convolutional fields of practice, as also to some new fields with more number of opportunities. Based on various categories of learning, numerous approaches have been suggested, including supervised, semi-supervised and unsupervised deep learning. The unsupervised deep learning aims to understand transferable image or video representations without manual annotations. Also, unsupervised approaches are needed when patterns that discern abnormal and normal behavior. In this paper, the recent development methods that are emerged in the domain of unsupervised deep learning are discussed. The various developments in the field of Auto Encoder are explained. The Deep learning structure like Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) is considered as a recent method which is in development for improving the accuracy and to perform the classification in an efficient way.

Related Papers

• → Implementing convolutional neural network model for prediction in medical imaging(2022)6 cited
• → Simultaneous Cell Detection and Classification with an Asymmetric Deep Autoencoder in Bone Marrow Histology Images(2017)8 cited
• → Deep Convolution Neural Network for RBC Images(2022)2 cited
• → A deep learning approach for stock market prediction using deep autoencoder and long short-term memory(2021)1 cited
• → Deep Convolutional Neural Networks(2021)8 cited