An Empirical Analysis of Generative Adversarial Network Training Times with Varying Batch Sizes

2020 ◽  
Author(s):  
Bhaskar Ghosh ◽  
Indira Kalyan Dutta ◽  
Albert Carlson ◽  
Michael Totaro ◽  
Magdy Bayoumi
Keyword(s):  
Empirical Analysis ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Network Training ◽  
Batch Sizes

scholarly journals DEM Void Filling Based on Context Attention Generation Model

2020 ◽  
Vol 9 (12) ◽  
pp. 734
Author(s):  
Chunsen Zhang ◽  
Shu Shi ◽  
Yingwei Ge ◽  
Hengheng Liu ◽  
Weihong Cui
Keyword(s):  
Interpolation Method ◽  
Digital Simulation ◽  
Generation Model ◽  
Generative Adversarial Network ◽  
Cloud Data ◽  
Adversarial Network ◽  
Network Training ◽  
Digital Elevation ◽  
Elevation Model ◽  
Feature Expression

The digital elevation model (DEM) generates a digital simulation of ground terrain in a certain range with the usage of 3D point cloud data. It is an important source of spatial modeling information. Due to various reasons, however, the generated DEM has data holes. Based on the algorithm of deep learning, this paper aims to train a deep generation model (DGM) to complete the DEM void filling task. A certain amount of DEM data and a randomly generated mask are taken as network inputs, along which the reconstruction loss and generative adversarial network (GAN) loss are used to assist network training, so as to perceive the overall known elevation information, in combination with the contextual attention layer, and generate data with reliability to fill the void areas. The experimental results have managed to show that this method has good feature expression and reconstruction accuracy in DEM void filling, which has been proven to be better than that illustrated by the traditional interpolation method.

scholarly journals Application of Generative Adversarial Nets (GANs) in Active Sound Production System of Electric Automobiles

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Kai Liang ◽  
Haijun Zhao
Keyword(s):  
Sound Production ◽  
Production Model ◽  
Audio Signals ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Moment Estimation ◽  
Network Training ◽  
Automobile Engines ◽  
Human Ear ◽  
Leave One Out

To improve the diversity and quality of sound mimicry of electric automobile engines, a generative adversarial network (GAN) model was used to construct an active sound production model for electric automobiles. The structure of each layer in the network in this model and the size of its convolution kernel were designed. The gradient descent in network training was optimized using the adaptive moment estimation (Adam) algorithm. To demonstrate the quality difference of the generated samples from different input signals, two GAN models with different inputs were constructed. The experimental results indicate that the model can accurately learn the characteristic distributions of raw audio signals. Results from a human ear auditory test show that the generated audio samples mimicked the real samples well, and a leave-one-out (LOO) test show that the diversity of the samples generated from the raw audio signals was higher than that of samples generated from a two-dimensional spectrogram.

scholarly journals Empirical Analysis of Deep Convolutional Generative Adversarial Network for Ultrasound Image Synthesis

2021 ◽  
Vol 15 (1) ◽  
pp. 71-77
Author(s):  
Dheeraj Kumar ◽  
Mayuri A. Mehta ◽  
Indranath Chatterjee
Keyword(s):  
Empirical Analysis ◽  
Ultrasound Imaging ◽  
Ultrasound Image ◽  
Generative Adversarial Networks ◽  
Ultrasound Images ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Synthetic Images

Introduction: Recent research on Generative Adversarial Networks (GANs) in the biomedical field has proven the effectiveness in generating synthetic images of different modalities. Ultrasound imaging is one of the primary imaging modalities for diagnosis in the medical domain. In this paper, we present an empirical analysis of the state-of-the-art Deep Convolutional Generative Adversarial Network (DCGAN) for generating synthetic ultrasound images. Aims: This work aims to explore the utilization of deep convolutional generative adversarial networks for the synthesis of ultrasound images and to leverage its capabilities. Background: Ultrasound imaging plays a vital role in healthcare for timely diagnosis and treatment. Increasing interest in automated medical image analysis for precise diagnosis has expanded the demand for a large number of ultrasound images. Generative adversarial networks have been proven beneficial for increasing the size of data by generating synthetic images. Objective: Our main purpose in generating synthetic ultrasound images is to produce a sufficient amount of ultrasound images with varying representations of a disease. Methods: DCGAN has been used to generate synthetic ultrasound images. It is trained on two ultrasound image datasets, namely, the common carotid artery dataset and nerve dataset, which are publicly available on Signal Processing Lab and Kaggle, respectively. Results: Results show that good quality synthetic ultrasound images are generated within 100 epochs of training of DCGAN. The quality of synthetic ultrasound images is evaluated using Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM). We have also presented some visual representations of the slices of generated images for qualitative comparison. Conclusion: Our empirical analysis reveals that synthetic ultrasound image generation using DCGAN is an efficient approach. Other: In future work, we plan to compare the quality of images generated through other adversarial methods such as conditional GAN, progressive GAN.

scholarly journals Traffic Flow Online Prediction Based on a Generative Adversarial Network with Multi-Source Data

2021 ◽  
Vol 13 (21) ◽  
pp. 12188
Author(s):  
Tuo Sun ◽  
Bo Sun ◽  
Zehao Jiang ◽  
Ruochen Hao ◽  
Jiemin Xie
Keyword(s):  
Traffic Flow ◽  
Short Term Memory ◽  
Moving Average ◽  
Spatial Prediction ◽  
Design Management ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Moment Estimation ◽  
Batch Sizes ◽  
Continuous Feedback

Traffic prediction is essential for advanced traffic planning, design, management, and network sustainability. Current prediction methods are mostly offline, which fail to capture the real-time variation of traffic flows. This paper establishes a sustainable online generative adversarial network (GAN) by combining bidirectional long short-term memory (BiLSTM) and a convolutional neural network (CNN) as the generative model and discriminative model, respectively, to keep learning with continuous feedback. BiLSTM constantly generates temporal candidate flows based on valuable memory units, and CNN screens out the best spatial prediction by returning the feedback gradient to BiLSTM. Multi-dimensional indicators are selected to map the multi-view fusion local trend for accurate prediction. To balance computing efficiency and accuracy, different batch sizes are pre-tested and allocated to different lanes. The models are trained with rectified adaptive moment estimation (RAdam) by dividing the dataset into the training and testing sets with a rolling time-domain scheme. In comparison with the autoregressive integrated moving average (ARIMA), BiLSTM, generating adversarial network for traffic flow (GAN-TF), and generating adversarial network for non-signal traffic (GAN-NST), the proposed improved generating adversarial network for traffic flow (IGAN-TF) successfully generates more accurate and stable flows and performs better.

Early prediction for mode anomaly in generative adversarial network training: An empirical study

2020 ◽  
Vol 534 ◽  
pp. 117-138 ◽  
Author(s):  
Chenkai Guo ◽  
Dengrong Huang ◽  
Jianwen Zhang ◽  
Jing Xu ◽  
Guangdong Bai ◽  
...  
Keyword(s):  
Empirical Study ◽  
Early Prediction ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Network Training

scholarly journals Spatial Coevolution for Generative Adversarial Network Training

2021 ◽  
Vol 1 (2) ◽  
pp. 1-28
Author(s):  
Erik Hemberg ◽  
Jamal Toutouh ◽  
Abdullah Al-Dujaili ◽  
Tom Schmiedlechner ◽  
Una-May O’reilly
Keyword(s):  
Evolutionary Computation ◽  
Loss Function ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Network Training ◽  
Gradient Based ◽  
Selection Parameter ◽  
Improved Performance ◽  
Multiple Loss

Generative Adversarial Networks (GANs) are difficult to train because of pathologies such as mode and discriminator collapse. Similar pathologies have been studied and addressed in competitive evolutionary computation by increased diversity. We study a system, Lipizzaner, that combines spatial coevolution with gradient-based learning to improve the robustness and scalability of GAN training. We study different features of Lipizzaner’s evolutionary computation methodology. Our ablation experiments determine that communication, selection, parameter optimization, and ensemble optimization each, as well as in combination, play critical roles. Lipizzaner succumbs less frequently to critical collapses and, as a side benefit, demonstrates improved performance. In addition, we show a GAN-training feature of Lipizzaner: the ability to train simultaneously with different loss functions in the gradient descent parameter learning framework of each GAN at each cell. We use an image generation problem to show that different loss function combinations result in models with better accuracy and more diversity in comparison to other existing evolutionary GAN models. Finally, Lipizzaner with multiple loss function options promotes the best model diversity while requiring a large grid size for adequate accuracy.

ORGANIC (1).pdf

2017 ◽  
Author(s):  
Benjamin Sanchez-Lengeling ◽  
Carlos Outeiral ◽  
Gabriel L. Guimaraes ◽  
Alan Aspuru-Guzik
Keyword(s):  
Machine Learning ◽  
Learning Community ◽  
Chemical Species ◽  
Material Design ◽  
Organic Photovoltaic ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Photovoltaic Material

Molecular discovery seeks to generate chemical species tailored to very specific needs. In this paper, we present ORGANIC, a framework based on Objective-Reinforced Generative Adversarial Networks (ORGAN), capable of producing a distribution over molecular space that matches with a certain set of desirable metrics. This methodology combines two successful techniques from the machine learning community: a Generative Adversarial Network (GAN), to create non-repetitive sensible molecular species, and Reinforcement Learning (RL), to bias this generative distribution towards certain attributes. We explore several applications, from optimization of random physicochemical properties to candidates for drug discovery and organic photovoltaic material design.

Sign in / Sign up

Export Citation Format

Share Document