SPARSE REPRESENTATION LEARNING OF DATA BY AUTOENCODERS WITH &lt;em&gt;L&lt;/em&gt;&lt;sub&gt;1/2&lt;/sub&gt; REGULARIZATION

Li, Feng; Żurada, Jacek M.; Wu, Wei

doi:10.14311/nnw.2018.28.008

Cited by 9 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…based on the inverse of the expected Q and E[P] using the expected P. These expectations are calculated using specific formulas involving the covariance matrix of the uncorrupted data X. (Li et al 2018) is a modified version of the Robust Autoencoder (RAE) designed to enhance the autoencoder's resilience when dealing with noisy or corrupted input data. This enhancement is achieved through the use of a specific type of regularization known as L 2,1 regularization.…”

Section: Marginalized Denoising Autoencodermentioning

confidence: 99%

Autoencoders and their applications in machine learning: a survey

Berahmand,

Daneshfar,

Salehi

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

Autoencoders have become a hot researched topic in unsupervised learning due to their ability to learn data features and act as a dimensionality reduction method. With rapid evolution of autoencoder methods, there has yet to be a complete study that provides a full autoencoders roadmap for both stimulating technical improvements and orienting research newbies to autoencoders. In this paper, we present a comprehensive survey of autoencoders, starting with an explanation of the principle of conventional autoencoder and their primary development process. We then provide a taxonomy of autoencoders based on their structures and principles and thoroughly analyze and discuss the related models. Furthermore, we review the applications of autoencoders in various fields, including machine vision, natural language processing, complex network, recommender system, speech process, anomaly detection, and others. Lastly, we summarize the limitations of current autoencoder algorithms and discuss the future directions of the field.

show abstract

Section: Marginalized Denoising Autoencodermentioning

confidence: 99%

Autoencoders and their applications in machine learning: a survey

Berahmand,

Daneshfar,

Salehi

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

show abstract

“…From this idea, a fault detection model can be created with the following steps: By following these steps and using two most popular techniques for optimizing autoencoder (denoising Auto-Encoder [54], dAE, and sparse Auto-Encoder [55], sAE), four encoder models were created: dAE + OCSVM (dAESVM), sAE + OCSVM (sAESVM), dAE + iForest (dAEForest) and sAE + iForest (sAEForest). In addition to the detection function hyperparameters, CVRS also tunes the hyperparameters of these autoencoder-based models listed in Table 3 with their probability distributions.…”

Section: Deep Learningmentioning

confidence: 99%

Fusing convolutional generative adversarial encoders for 3D printer fault detection with only normal condition signals

Cabrera

Sancho

et al. 2021

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

Collecting data from mechanical systems in abnormal conditions is expensive and time consuming. Consequently, fault detection approaches based on classical supervised learning working with both normal and abnormal data are not applicable in some conditionbased maintenance tasks. To address this problem, this paper proposes Fusing Convolutional Generative Adversarial Encoders (fCGAE) method to create fault detection models from only normal data. Firstly, to obtain an adequate deep feature space, encoder models based on 1D convolutional neural networks are created. Then, these encoders are optimized in an unsupervised way through Bidirectional Generative Adversarial Networks. Finally, the multi-channel features collected from the system are merged with One-Class Support Vector Machine. fCGAE is applied to fault detection in 3D printers, where experimental results in two fault detection cases show excellent generalization capabilities and better performance compared to peer methods.

show abstract

“…Lastly, in generative models our approach is relevant for reconstructing images from their parts similar to [9]. Since we are trying to create a model where missing features are defining a class, we could also provide what features are missing and also where.…”

Section: Future Workmentioning

confidence: 99%

Classification Based on Missing Features in Deep Convolutional Neural Networks

Milošević¹,

Racković²

2019

NNW

View full text Add to dashboard Cite

Artificial Neural Networks, notably Convolutional Neural Networks (CNN) are widely used for classification purposes in different fields such as image classification, text classification and others. It is not uncommon therefore that these models are used in critical systems (e.g. self-driving cars), where robustness is a very important attribute. All Convolutional Neural Networks used for classification, classify based on the extracted features found in the input sample. In this paper, we present a novel approach of doing the opposite-classification based on features not present in the input sample. Obtained results show not only that this way of learning is indeed possible but also that the trained models become more robust in certain scenarios. The presented approach can be applied to any existing Convolutional Neural Network model and does not require any additional training data.

show abstract

SPARSE REPRESENTATION LEARNING OF DATA BY AUTOENCODERS WITH <em>L</em><sub>1/2</sub> REGULARIZATION

Cited by 9 publications

References 21 publications

Autoencoders and their applications in machine learning: a survey

Autoencoders and their applications in machine learning: a survey

Fusing convolutional generative adversarial encoders for 3D printer fault detection with only normal condition signals

Classification Based on Missing Features in Deep Convolutional Neural Networks

Contact Info

Product

Resources

About