Autoencounter in Machine Learning
DOI:
https://doi.org/10.61173/p7hxhp58Keywords:
Autoencoders, Dimensionality Reduction, Feature Extraction, Unsupervised Learning, Generative Models, Anomaly Detection, Image DenoisingAbstract
An Autoencoder is a type of neural network model that learns compressed, encoded representations of data, usually for dimensionality reduction or feature extraction. Despite its apparent simplicity, autoencoder serves a vital role in machine learning, particularly in applications that need unsupervised learning.
References
LeCun, Yann, et al. "Deep Learning." Nature, vol. 521, 2015, pp. 436-444. Ng, Andrew. "Sparse Autoencoder." CS294A Lecture Notes,
Stanford University, 2011. hhhhhttps://web.stanford.edu/class/ cs294a/sparseAutoencoder_2011new.pdf. Vincent, Pascal, et al. "Stacked Denoising Autoencoders: Learning Useful hhhhRepresentations in a Deep Network with a Local Denoising Criterion." Journal of hhhhMachine Learning
Research, vol. 11, 2010, pp. 3371-3408. hhhhhttps://www.jmlr. org/papers/volume11/vincent10a/vincent10a.pdf. Zhang, Yi, et al. "Convolutional Autoencoders." Neural
Networks, vol. 30, 2012, pp. hhhh167-182. https://www. sciencedirect.com/science/article/pii/S0893608012000406.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
