检索结果-内蒙古大学图书馆

Unveiling the relationship between Fabry-Perot laser structures and optical field distribution via symbolic regression

引用

Optoelectronics Letters 2025年第3期21卷 149-154页

作者： LI Wenqiang WU Min LI Weijun HAO Meilan YU Lina AnnLab Institute of SemiconductorsChinese Academy of SciencesBeijing100083China School of Electronic Electrical and Communication Engineering&School of Integrated CircuitsUniversity of Chinese Academy of SciencesBeijing100049China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing100083China

In recent years,machine learning(ML)techniques have been shown to be effective in accelerating the development process of optoelectronic ***,as"black box"models,they have limited theoretical *** this work,we leverage symbolic regression(SR)technique for discovering the explicit symbolic relationship between the structure of the optoelectronic Fabry-Perot(FP)laser and its optical field distribution,which greatly improves model transparency compared to *** demonstrated that the expressions explored through SR exhibit lower errors on the test set compared to ML models,which suggests that the expressions have better fitting and generalization capabilities.

关键词： machine learning optoelectronic deviceshoweverasblack optical field distributionwhich symbolic regression symbolic regression sr technique Fabry Perot laser discovering explicit symbolic relationship optical field distribution

来源：评论

学校读者我要写书评

暂无评论

Learning to represent 2D human face with mathematical model

引用

CAAI Transactions on Intelligence technology 2024年第1期9卷 54-68页

作者： Liping Zhang Weijun Li Linjun Sun Lina Yu Xin Ning Xiaoli Dong AnnLab Institute of SemiconductorsChinese Academy of SciencesBeijingChina Center of Materials Science and Optoelectronics Engineering School of Integrated CircuitsUniversity of Chinese Academy of SciencesBeijingChina Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology BeijingChina

How to represent a human face pattern?While it is presented in a continuous way in human visual system,computers often store and process it in a discrete manner with 2D arrays of *** authors attempt to learn a continuous surface representation for face image with explicit ***,an explicit model(EmFace)for human face representation is pro-posed in the form of a finite sum of mathematical terms,where each term is an analytic function ***,to estimate the unknown parameters of EmFace,a novel neural network,EmNet,is designed with an encoder-decoder structure and trained from massive face images,where the encoder is defined by a deep convolutional neural network and the decoder is an explicit mathematical expression of *** authors demonstrate that our EmFace represents face image more accurate than the comparison method,with an average mean square error of 0.000888,0.000936,0.000953 on LFW,IARPA Janus Benchmark-B,and IJB-C *** results show that,EmFace has a higher representation performance on faces with various expressions,postures,and other ***,EmFace achieves reasonable performance on several face image processing tasks,including face image restoration,denoising,and transformation.

关键词： artificial neural networks face analysis image processing mathematics computing

来源：评论

学校读者我要写书评

暂无评论

General nonlinear function neural network fitting algorithm based on CNN 3

General nonlinear function neural network fitting algorithm ...

引用

3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022

作者： Xu, Xintao Jiang, Zhelong Chen, Gang Li, Zhigang Gong, Guoliang Lu, Huaxiang University of Science and Technology of China School of Microelectronics Hefei China Institute of Semiconductors Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Materials and Optoelectronics Research Center Beijing China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Laboratory Beijing China

ISBN: (纸本)9781665459112

This paper proposes a generic neural network fitting algorithm based on CNN for nonlinear functions that overcomes the challenges of a large number of nonlinear functions in terms of hardware deployment and computing circuit generality in diverse neural network models. The model takes advantage of the principle that functions have varying degrees of difficulty fitting in different spaces, mapping the input to high-dimensional space with 1x1 convolution, and utilizing CNN to extract features of nonlinear functions with its strong feature extraction ability in high-dimensional space. Furthermore, MaxPool and ReLU improve the ability of nonlinear fitting. When fitting Tanh, Sigmoid, and ELU activation functions with 16bit accuracy, the proposed algorithm has an average error of less than 0.0006, with a parameter size of 5.793 k. © 2022 IEEE.

关键词： Functions

来源：评论

学校读者我要写书评

暂无评论

A Novel Configurable High-precision and Low-cost Circuit Design of Sigmoid and Tanh Activation Function

A Novel Configurable High-precision and Low-cost Circuit Des...

引用

2021 IEEE International Conference on Integrated Circuits, Technologies and Applications, ICTA 2021

作者： Liu, Feng Zhang, Bowen Chen, Gang Gong, Guoliang Lu, Huaxiang Li, Wenchang Chinese Academy of Sciences Institute of Semiconductors Beijing100083 China University of Chinese Academy of Sciences Beijing100089 China Center for Excellence in Brain Science and Intelligence Technology CAS Shanghai200031 China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Lab Beijing100083 China

ISBN: (纸本)9781665417471

This paper proposes a configurable Sigmoid and Tanh activation function circuit design by second-order approximation and deviation compensation. The proposed circuit is synthesized in TSMC 180nm technology within a 7218 um2 area at 500MHz, it is also deployed on Xilinx ZC706 FPGA by 158 LUTs and 46 FFs at 333MHz. It achieves almost 4.68× better precision and 20.2% less area than previous works. The experimental results show that our method has almost no accuracy loss on LSTM Chinese speech recognition tasks and the YOLOv3 image recognition post-processing task. © 2021 IEEE.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

PGGAN: Improve Password Cover Rate Using the Controller

PGGAN: Improve Password Cover Rate Using the Controller

引用

2021 International Conference on Computer network Security and Software Engineering, CNSSE 2021

作者： Guo, Xiaozhou Liu, Yi Tan, Kaijun Jin, Min Lu, Huaxiang Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China University of Chinese Academy of Sciences Beijing100089 China Cas Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Beijing200031 China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Lab Beijing100083 China

Password generation model based on generative adversarial network usually has the problem of high duplicate rate, which further leads to low cover rate. In this regard, we propose PGGAN model. It sets up an additional controller network which is similar to the discriminator in the aspect of structure and function. The discriminator and the controller respectively learn the measure between the distribution of generated password with the real password distribution and the uniform distribution, and then use two measures to teach generator meanwhile. By changing the activation function and loss function of the controller, different measure functions can be selected. The experimental results show that compared with GAN, our PGGAN performs better both in cover rate and duplicate rate. Moreover, Wasserstein distance usually has a better effect to the other measure in model. Specifically, PGGAN with Wasserstein distance can increase the cover rate by 3.57% and reduce the duplicate rate by 30.85% on rockyou dataset. © Published under licence by IOP Publishing Ltd.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Sdgan: Improve Speech Enhancement Quality by Information Filter 6

Sdgan: Improve Speech Enhancement Quality by Information Fil...

引用

2021 6th International Symposium on Advances in Electrical, Electronics and Computer Engineering, ISAEECE 2021

作者： Guo, Xiaozhou Liu, Yi Mao, Wenyu Li, Jixing Li, Wenchang Gong, Guoliang Lu, Huaxiang Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China University of Chinese Academy of Sciences Beijing100089 China CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Beijing200031 China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Lab Beijing100083 China

The speech denoising model based on adversarial generative network has achieved better results than the traditional machine learning model. In this paper, for the short cut connection in the generator, we discuss its influence on the information transfer between encoder and decoder, and propose SDGAN at target. SDGAN sets linear and convolution filters in the short cut connection which adaptively learn the optimal information processing. The information filter still enables the generator to solve the gradient vanishing problem, and it can also avoid information redundancy and improve expression ability. In addition, SDGAN replaces the L1 regularization term in loss function with the L2 regularization term, which not only makes the output speech of the generator closer to the clean speech, but also avoids sparsity. In the experiments, SDGAN significantly performs better than other traditional GAN in five performance metrics (such as PESQ), and the effect of convolution filter is better than that of linear filter. © Published under licence by IOP Publishing Ltd.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Mathematical representation of 2D image boundary contour using fractional implicit polynomial

引用

Optoelectronics Letters 2023年第4期19卷 252-256页

作者： TONG Yuerong YU Lina LI Weijun LIU Jingyi WU Min YANG Yafei Institute of Semiconductors Chinese Academy of SciencesBeijing 100083China School of Materials Science and Optoelectronic Technology&School of Integrated Circuits University of Chinese Academy of SciencesBeijing 100049China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing 100083China DapuStor Corporation Shenzhen 518100China

Implicit polynomial(IP)fitting is an effective method to quickly represent two-dimensional(2D)image boundary contour in the form of mathematical *** the same maximum degree,the fractional implicit polynomial(FIP)can express more curve details than IP and has obvious advantages for the representation of complex boundary *** existing studies,algebraic distance is mainly used as the fitting objective of the *** the time cost is reduced,there are problems of low fitting accuracy and spurious zero *** this paper,we propose a two-stage neural network with differentiable geometric distance,which uses FIP to achieve mathematical representation,called *** the first stage,the continuity constraint is used to obtain a rough outline of the fitting *** the second stage,differentiable geometric distance is gradually added to fine-tune the polynomial coefficients to obtain a contour representation with higher *** results show that TSEncoder can achieve mathematical representation of 2D image boundary contour with high accuracy.

关键词： polynomial contour representation

来源：评论

学校读者我要写书评

暂无评论

Blind image quality assessment based on the multiscale and dual-domains features fusion

Blind image quality assessment based on the multiscale and d...

引用

作者： Lu, Yaxuan Li, Weijun Ning, Xin Dong, Xiaoli Zhang, Liping Sun, Linjun Cheng, Chuantong Institute of Semiconductors Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China School of Microelectronics University of Chinese Academy of Sciences Beijing China Cognitive Computing Technology Joint Laboratory Wave Group Beijing China

Image quality assessment is to simulate subjective human visual perception and realize image quality inference automatically. Although deep neural networks have achieved great success, the majority of them do not fully consider perception characteristics. Therefore, according to the human visual scale characteristics, we proposed an image quality assessment algorithm based on multiscale and dual domains fusion. Firstly, the original image and its phase congruency respectively input into two branches, feature pyramid and channel attention mechanism are adopted to extract multiscale features. After that, bilinear pool is used to aggregate the spatial and frequency domain characteristics of the corresponding scales, and allows arbitrary scale input to ensure that the features are extracted from the inherent quality images. Finally, the single quality score is obtained through learned weights of each scale. Comparative experiments between our approach and state-of-the-art are conducted on five public databases, the results demonstrate that the proposed algorithm is not only robust to different types and across database, but also sensitive to scale. © 2021 John Wiley & Sons, Ltd.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Research on Convolution Decomposition and Hardware Acceleration based on FPGA 4

Research on Convolution Decomposition and Hardware Accelerat...

引用

4th International Conference on Computer Engineering and Application, ICCEA 2023

作者： He, Jinzhong Li, Weijun Xu, Jian Zhang, Ming Yang, Huiqu Institute of Semiconductors Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China DapuStor Corporation Shenzhen China

ISBN: (纸本)9798350347548

Convolutional neural network (CNN) is an artificial intelligence algorithm with a wide application foundation. In recent years, to improve the computational speed of the computation-intensive CNN models, many researchers have accelerated hardware implementation on FPGA. However, the acceleration algorithms are mostly unfriendly to hardware or have poor flexibility, which leads to a decrease in computing power and an increase in data access. In this paper, we propose a convolution decomposition method in the time domain, which fully considers the behavior of convolution operation and the difference between data streams in hardware. Besides, we design a hardware acceleration architecture. The results show that this design can be compatible with convolution and full connection operations of various sizes and strides. Hardware tailoring and cascade expansion are proposed for different application scenarios. Experiments show that the computing performance per DSP is 0.39 GOP/s, which demonstrates that the hardware design has a better multiplier utilization than similar works. © 2023 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

RLEPSO: Reinforcement learning based Ensemble particle swarm optimizer 4

RLEPSO: Reinforcement learning based Ensemble particle swarm...

引用

4th International Conference on Algorithms, computing and Artificial Intelligence, ACAI 2021

作者： Yin, Shiyuan Liu, Yi Gong, GuoLiang Lu, Huaxiang Li, Wenchang Institute of Semiconductors Chinese Academy of Sciences Beijing China Institute of Semiconductors Chinese Academy of Sciences University of Chinese Academy of Sciences China Academy of Sciences Brain Science and Intelligent Technology Excellence Innovation Center Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China

ISBN: (纸本)9781450385053

Evolution is the driving force behind the evolution of biological intelligence. Learning is the driving force behind human civilization. The combination of evolution and learning can form an entire natural world. Now, reinforcement learning has shown significant effects in many places. However, Currently, researchers in the field of optimization algorithms mainly focus on evolution strategies. And there is very little research on learning. Inspired by these ideas, this paper proposes a new particle swarm optimization algorithm Reinforcement learning based Ensemble particle swarm optimizer (RLEPSO) that combines reinforcement learning. The algorithm uses reinforcement learning for pre-training in the design phase to automatically find a more effective combination of parameters for the algorithm to run better and Complete optimization tasks faster. Besides, this algorithm integrates two robust particle swarm variants. And it sets the weight parameters for different algorithms to better adapt to the solution requirements of a variety of different optimization problems, which significantly improves the robustness of the algorithm. RLEPSO makes a certain number of sub-swarms to increase the probability of finding the global optimum and increasing the diversity of particle swarms. This proposed RLEPSO is evaluated on an optimization test functions benchmark set (CEC2013) with 28 functions and compared with other eight particle swarm optimization variants, including three state-of-the-art optimization algorithms. The results show that RLEPSO has better performance and outperforms all compared algorithms. © 2021 Owner/Author.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：