The effect of whitening transformation on pooling operations in convolutional autoencoders

Li, Zuhe; Fan, Yangyu; Liu, Weihua

doi:10.1186/s13634-015-0222-1

Cited by 19 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted that Eq. ( 3) corresponds to the so-called whitening 57,58 , where the data is transformed to exhibit zero mean and unity standard deviation. The last format is min-max normalization, defined as Herein, max(|X zc |) defines selection of column-vise maximum element.…”

Section: Proposed Modeling Approach: Fully Adaptive Regression Modelmentioning

confidence: 99%

Deep-learning-based precise characterization of microwave transistors using fully-automated regression surrogates

Çalık

Güneş

Kozieł

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Accurate models of scattering and noise parameters of transistors are instrumental in facilitating design procedures of microwave devices such as low-noise amplifiers. Yet, data-driven modeling of transistors is a challenging endeavor due to complex relationships between transistor characteristics and its designable parameters, biasing conditions, and frequency. Artificial neural network (ANN)-based methods, including deep learning (DL), have been found suitable for this task by capitalizing on their flexibility and generality. Yet, rendering reliable transistor surrogates is hindered by a number of issues such as the need for finding good match between the input data and the network architecture and hyperparameters (number and sizes of layers, activation functions, data pre-processing methods), possible overtraining, etc. This work proposes a novel methodology, referred to as Fully Adaptive Regression Model (FARM), where all network components and processing functions are automatically determined through Tree Parzen Estimator. Our technique is comprehensively validated using three examples of microwave transistors and demonstrated to offer a competitive edge over the state-of-the-art methods in terms of modeling accuracy and handling the aforementioned issues pertinent to standard ANN-based surrogates.

show abstract

Section: Proposed Modeling Approach: Fully Adaptive Regression Modelmentioning

confidence: 99%

Deep-learning-based precise characterization of microwave transistors using fully-automated regression surrogates

Çalık

Güneş

Kozieł

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…A Pooling layer in a convolutional network combines the outputs of neuron clusters in the previous layer to reduce the resolution of feature maps and achieve spatial invariance [9,10,27]. After pooling operation, computational cost is reduced and over-fitting can be avoided.…”

Section: Pooling Layermentioning

confidence: 99%

“…The pooling region can overlap each other in varying sizes [27]. Though several pooling methods have been proposed, average pooling and max pooling are still the most common methods.…”

Section: Pooling Layermentioning

confidence: 99%

Unsupervised Feature Learning Assisted Visual Sentiment Analysis

Li¹,

Fan²,

Wang

et al. 2016

IJMUE

Self Cite

View full text Add to dashboard Cite

show abstract

“…Specifically, the SAE model hopes the neural network can recover input data through training, namelyx ðiÞ ¼ W white x ðiÞ . Considering the constraint of weight attenuation and implicit responses' sparsity, the overall cost function can be expressed as Formula (3) [11,12]:…”

Section: Saementioning

confidence: 99%

Classification methods of a small sample target object in the sky based on the higher layer visualizing feature and transfer learning deep networks

Chen

Meng

Wen

et al. 2018

J Wireless Com Network

View full text Add to dashboard Cite

The effective classification methods of the small target objects in the no-fly zone are of great significance to ensure safety in the no-fly zone. But, due to the differences of the color and texture for the small target objects in the sky, this may be unobvious, such as the birds, unmanned aerial vehicles (UAVs), and kites. In this paper, we introduced the higher layer visualizing feature extraction method based on the hybrid deep network model to obtain the higher layer feature through combining the Sparse Autoencoder (SAE) model, the Convolutional Neural Network (CNN) model, and the regression classifier model to classify the different types of the target object images. In addition, because the sample numbers of the small sample target objects in the sky may be not sufficient, we cannot obtain much more local features directly to realize the classification of the target objects based on the higher layer visualizing feature extraction; we introduced the transfer learning in the SAE model to gain the cross-domain higher layer local visualizing features and sent the cross-domain higher layer local visualizing features and the images of the target-domain small sample object images into the CNN model, to acquire the global visualizing features of the target objects. Experimental results have shown that the higher layer visualizing feature extraction and the transfer learning deep networks are effective for the classification of small sample target objects in the sky.

show abstract

The effect of whitening transformation on pooling operations in convolutional autoencoders

Cited by 19 publications

References 14 publications

Deep-learning-based precise characterization of microwave transistors using fully-automated regression surrogates

Deep-learning-based precise characterization of microwave transistors using fully-automated regression surrogates

Unsupervised Feature Learning Assisted Visual Sentiment Analysis

Classification methods of a small sample target object in the sky based on the higher layer visualizing feature and transfer learning deep networks

Contact Info

Product

Resources

About