Abstract
Autoencoder is an unsupervised learning technique widely used over different types of data that gets the output exactly like the input. The major usage of autoencoders lie in feature extraction, dimensionality reduction, image denoising, compression, etc. This paper concentrates on the implementation of undercomplete, sparse and variational autoencoder over the Modified National Institute of Standards and Technology (MNIST) dataset and analyse the efficiency using loss and activation function. The effect of the number of epochs in building the model is also analysed. For the dataset, sparse autoencoder performs better than the undercomplete when implemented with Adam as an activation function with mean square error as loss function. When compared with the variational autoencoder (VAE), VAE performs better when implemented using Adam function.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
