An Evaluation Study on Circuit Parameter Conditions of Neural Network Controlled DC-DC Converter

2013 ◽  
Author(s):  
Hidenori Maruta ◽  
Masashi Motomura ◽  
Fujio Kurokawa
Keyword(s):  
Neural Network ◽  
Evaluation Study ◽  
Circuit Parameter

scholarly journals Depth-Aware Arbitrary Style Transfer Using Instance Normalization

2020 ◽  
pp. paper2-1-paper2-11
Author(s):  
Victor Kitov ◽  
Konstantin Kozlovtsev ◽  
Margarita Mishustina
Keyword(s):  
Neural Network ◽  
Qualitative Analysis ◽  
Loss Function ◽  
Human Perception ◽  
Depth Map ◽  
Evaluation Study ◽  
User Evaluation ◽  
Style Transfer ◽  
Separate Model ◽  
Transfer Method

Style transfer is the process of rendering one image with some content in the style of another image, representing the style. Recent studies of Liu et al. (2017) show that traditional style transfer methods of Gatys et al. (2016) and Johnson et al.(2016) fail to reproduce the depth of the content image, which is critical for human perception. They suggest to preserve the depth map by additional regularizer in the optimized loss function, forcing preservation of the depth map. However these traditional methods are either computationally inefficient or require training a separate neural network for each style. AdaIN method of Huang et al. (2017) allows efficient transferring of arbitrary style without training a separate model but is not able to reproduce the depth map of the content image. We propose an extension to this method, allowing depth map preservation by applying variable stylization strength. Qualitative analysis and results of user evaluation study indicate that the proposed method provides better stylizations, compared to the original AdaIN style transfer method.

scholarly journals Cross-species cell-type assignment of single-cell RNA-seq by a heterogeneous graph neural network

2021 ◽  
Author(s):  
Xingyan Liu ◽  
Qunlun Shen ◽  
Shihua Zhang
Keyword(s):  
Neural Network ◽  
Single Cell ◽  
Cell Types ◽  
Evaluation Study ◽  
Systematic Evaluation ◽  
Homologous Gene ◽  
Cell Type ◽  
Evolutionary Mechanisms ◽  
Comparative Analyses ◽  
Type Assignment

Cross-species comparative analyses of single-cell RNA sequencing (scRNA-seq) data allow us to explore, at single-cell resolution, the origins of cellular diversity and the evolutionary mechanisms that shape cellular form and function. Here, we aimed to utilize a heterogeneous graph neural network to learn aligned and interpretable cell and gene embeddings for cross-species cell type assignment and gene module extraction (CAME) from scRNA-seq data. A systematic evaluation study on 649 pairs of cross-species datasets showed that CAME outperformed six benchmarking methods in terms of cell-type assignment and model robustness to insufficiency and inconsistency of sequencing depths. Comparative analyses of the major types of human and mouse brains by CAME revealed shared cell type-specific functions in homologous gene modules. Alignment of the trajectories of human and macaque spermatogenesis by CAME revealed conservative gene expression dynamics during spermatogenesis between humans and macaques. Owing to the utilization of non-one-to-one homologous gene mappings, CAME made a significant improvement on cell-type characterization cross zebrafish and other species. Overall, CAME can not only make an effective cross-species assignment of cell types on scRNA-seq data but also reveal evolutionary conservative and divergent features between species.

The Evaluation Study of Supply Chain Financial Risk Based on the BP Neural Network

2013 ◽  
Vol 401-403 ◽  
pp. 2306-2309 ◽  
Author(s):  
Lin Si Hang Qiao ◽  
Zhi Hong Lin
Keyword(s):  
Neural Network ◽  
Supply Chain ◽  
Credit Risk ◽  
Bp Neural Network ◽  
Financial Services ◽  
Commercial Banks ◽  
Financial Risk ◽  
Evaluation Study ◽  
Evaluation Index System ◽  
Supply Chain Financing

In recent years, the supply chain financial has become the focus of attention of the many financial institutions, because the supply chain financing model is to make full use of the supply chain and the characteristics of small and medium-sized enterprise designed. It is not only the effective way of small and medium-sized enterprises in China to solve the difficulty of financing, but also is an effective way of the Commercial Banks expand financial services [ . This paper firstly constructed the financial credit risk evaluation index system of small and medium-sized enterprise based on supply chain, through the BP neural network model analyze credit risk of small and medium-sized enterprise, then predicted their financing credit level, to provide the basis for Commercial Banks for credit.

scholarly journals Regularisation of neural networks by enforcing Lipschitz continuity

2020 ◽  
Author(s):  
Henry Gouk ◽  
Eibe Frank ◽  
Bernhard Pfahringer ◽  
Michael J. Cree
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Lipschitz Continuity ◽  
Simple Technique ◽  
Lipschitz Constant ◽  
Gradient Methods ◽  
Evaluation Study ◽  
Training Data ◽  
Feed Forward Neural Network ◽  
Performance Gains

AbstractWe investigate the effect of explicitly enforcing the Lipschitz continuity of neural networks with respect to their inputs. To this end, we provide a simple technique for computing an upper bound to the Lipschitz constant—for multiple p-norms—of a feed forward neural network composed of commonly used layer types. Our technique is then used to formulate training a neural network with a bounded Lipschitz constant as a constrained optimisation problem that can be solved using projected stochastic gradient methods. Our evaluation study shows that the performance of the resulting models exceeds that of models trained with other common regularisers. We also provide evidence that the hyperparameters are intuitive to tune, demonstrate how the choice of norm for computing the Lipschitz constant impacts the resulting model, and show that the performance gains provided by our method are particularly noticeable when only a small amount of training data is available.

Sign in / Sign up

Export Citation Format

Share Document