Citation :

AnNing, Mazida Ahmad, Huda lbrahim, 2024. "Variational Autoencoders: A Deep Generative Model for Unsupervised Learning" ESP International Journal of Communication Engineering & Electronics Technology (ESP- IJCEET)  Volume 2, Issue 1 : 55-60

.

Abstract :

Variational Autoencoders (VAEs) have become a popular deep generative model for unsupervised learning. This paper aims to investigate the effectiveness of VAEs in learning latent representations and generating meaningful samples. By leveraging the recognition and generative models in VAEs, a variational lower bound on the data log-likelihood can be optimized through backpropagation. Through experiments on a variety of datasets, including MNIST and CIFAR-10, it is demonstrated that VAEs can capture complex latent structures and generate high-quality samples with diverse variations. Furthermore, the learned latent representations exhibit desirable properties such as disentangling factors of variation. In conclusion, VAEs have shown great promise as a deep generative model for unsupervised learning, offering a powerful tool for various applications in computer vision and natural language processing.

References :

[1] D Al Chanti.Analyse Automatique des Macro et Micro Expressions Faciales : Détection et Reconnaissance par Machine Learning[D].,2019
[2] S Sadok,S Leglaive,L Girin,et al.Learning and controlling the source-filter representation of speech with a variational autoencoder[D].,2022
[3] M Sadeghi, P Magron.A Sparsity-promoting Dictionary Model for Variational Autoencoders[D].,2022
[4] L Girin,S Leglaive,X Bie,et al.Dynamical Variational Autoencoders: A Comprehensive Review[D].Foundations & Trends in Machine Learning,2022
[5] M Mathieu.Unsupervised Learning under Uncertainty.[D].,2017
[6] S Lander.An evolutionary method for training autoencoders for deep learning networks.[D].,2014
[7] M Memarzadeh, B Matthews, I Avrekh.Unsupervised Anomaly Detection in Flight Data Using Convolutional Variational Auto-Encoder[D].,2020
[8] MTH De Frahan,S Yellapantula,R King,et al.Deep learning for presumed probability density function models[D].Combustion & Flame,2019
[9] DS Nandy. Variational Autoencoder Coupled with Deep Generative Neural Network for the Identification of Handwritten Digits[D]. International Journal of Applied Engineering Research,2018
[10] Dongfang,Wang,Jin,et al.VASC: Dimension Reduction and Visualization of Single-cell RNA-seq Data by Deep Variational Autoencoder[D].Genomics, Proteomics & Bioinformatics,2018
[11] X Wang, Y Du, S Lin, et al.adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection[D].,2019
[12] Y; Tang,K; Kojima,T; Koike-Akino,et al.Generative Deep Learning Model for Inverse Design of Integrated Nanophotonic Devices[D].Laser & Photonics Review,2020
[13] Z Zhai,Z Liang,W Zhou,et al.Research Overview of Variational Auto-Encoders Models[D].Computer Engineering & Applications,2019
[14] Hu Fang,Niklas Wittmer,Johannes Twiefel,et al.Partially Adaptive Multichannel Joint Reduction of Ego-noise and Environmental Noise[D].,2023
[15] A Kuzina,E Egorov,E Burnaev.BooVAE: Boosting Approach for Continual Learning of VAE[D].,2019

Keywords :

Variational Autoencoders, Deep Generative Model, Unsupervised Learning.