检索结果-内蒙古大学图书馆

7th Asian Conference on Artificial Intelligence technology, ACAIT 2023

作者： Tong, Yuerong Yu, Lina Li, Weijun Liu, Jingyi Hou, Luyang Sun, Linjun Wu, Min Chinese Academy of Sciences AnnLab Institute of Semiconductors Beijing100085 China University of Chinese Academy of Sciences School of Materials Science And Optoelectronic Technology School of Integrated Circuits Beijing100049 China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing And Computing Technology Beijing100085 China Beijing University of Posts And Telecommunications Beijing100876 China

ISBN: (纸本)9798350359145

Implicit polynomial can efficiently represent the object contour for the curve fitting, and fractional implicit polynomial (FIP) is capable of describing complex objects at lower degree. However, both of IP and FIP based curve fitting methods suffer from the problem of insufficient fitting accuracy because of spurious zero sets. In this paper, we propose a particle swarm optimization (PSO)-assisted monomial combination optimization framework to fit curves based on FIP. In the proposed PSO-FIP framework, we adopt a monomial combination optimization strategy to remove redundant monomials and reduce spurious zero sets accordingly. And then, we solve the combinatorial explosion problem by using PSO in the monomial combination optimization. We further propose a geometric distance metric to serve as the fitness function in PSO which overcomes the trivial solution problem of algebraic distance. We conduct extensive experiments to validate the PSO-FIP framework and the results demonstrate that our approach can achieve higher accuracy with fewer coefficients in curve fitting. © 2023 IEEE.

关键词： Curve fitting

来源：评论

学校读者我要写书评

暂无评论

SSCGAN: Speech style conversion based on GAN

SSCGAN: Speech style conversion based on GAN

引用

2022 International Conference on Algorithms, Microchips and network Applications

作者： Li, Jixing Guo, Xiaozhou Shen, Ronxuan Lu, Huaxiang Wang, Xinggang Cao, Zhanzhong Zhang, Chi Mao, Wenyu Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China University of Chinese Academy of Sciences Beijing100089 China Materials and Optoelectronics Research Center University of Chinese Academy of Sciences Beijing100083 China College of Microelectronics University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Laboratory Beijing100083 China Nanjing Research Institute of Information Technology Nanjing210009 China

ISBN: (纸本)9781510653290

Speech conversion has significant applications in medical, robotics, and other industries. With the rise of deep learning, CycleGAN is widely used in speech conversion technology. However, the existing CycleGAN-based methods do not consider the speech signal's temporal and spatial features. In addition, the training of CycleGAN is difficult to converge due to the gradient disappearance problem of the generator. We propose SSCGAN, whose generator is a U-shaped encoder-decoder network that extracts the temporal and spatial features by using 1DCNN and 2DCNN in parallel. A feature fusion module based on multi-scale mixed convolution is embedded between encoder and decoder to achieve high-level fusion of spatial features and temporal features. To make the network training more stable and easier to converge, SSCGAN uses Wasserstein distance instead of the original Jensen-Shannon divergence to calculate the distance of the probability distribution, which can alleviate the gradient extinction problem for generators. In addition, SSCGAN utilizes the PatchGAN structure in the discriminator, which considers the samples' local details by dividing them into different patches. It can improve the discriminative ability of SSCGAN. The experiment results in the nonparallel corpus database VCC 2018 show that SSCGAN is superior to existing methods such as CycleGAN-VC, StarGan-VC. In inter-gender speech conversion, the MSD of SSCGAN is decreased by 0.162 on average compared to other methods, and in intra-gender speech conversion, the MSD is decreased by 0.118 on average. In subjective evaluation, participants also think SSCGAN is the best. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Generative adversarial networks

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

IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)

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

ISBN: (纸本)9781665417488

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 um 2 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.

关键词： Integrated circuit technology Image recognition Costs Conferences Speech recognition Hardware Circuit synthesis

来源：评论

学校读者我要写书评

暂无评论

Artificial neural network-based Approach to Modeling Energy Bands of GaN-based Heterojunction Materials 5

Artificial Neural Network-based Approach to Modeling Energy ...

引用

5th International Conference on High Performance Big Data and intelligent Systems, HDIS 2023

作者： Hao, Meilan Wei, Shu Yu, Lina Li, Weijun Wu, Min Liu, Jingyi Li, Wenqiang Li, Yanjie AnnLab Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China School of Information and Electrical Engineering Hebei University of Engineering Handan056038 China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing100083 China School of Integrated Circuits University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9798350394160

This work reports a preliminary investigation of energy bands of AlxGa1-xN/GaN heterojunction based on the use of artificial neural networks (ANN). Numerical energy bands simulations were used to generate training and testing dataset for ANN *** input parameters of the ANN are the Al content,the thicknesses of AlxGa1-xN barrier layer and position description of two-Layer Materials, respectively. The outputs of the ANN are the conduction band energy profile of theAlxGa1-xN/GaN heterojunction and the channel Two-dimensional electron gas (2DEG) concentration *** results show that trained ANN model can effectively predict the energy bands structure. The model achieved a mean squared error of 7.94 × 10 6 on the testing dataset, with an average relative L2 error of 4.44×10 3 for electron concentration prediction and 2.57×10 3 for conduction band energy prediction. ©2023 IEEE.

关键词： Heterojunctions

来源：评论

学校读者我要写书评

暂无评论

A neural-Guided Dynamic Symbolic network for Exploring Mathematical Expressions from Data 41

A Neural-Guided Dynamic Symbolic Network for Exploring Mathe...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Wenqiang Li, Weijun Yu, Lina Wu, Min Sun, Linjun Liu, Jingyi Li, Yanjie Wei, Shu Deng, Yusong Hao, Meilan AnnLab Institute of Semiconductors Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering School of Integrated Circuits University of Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of Sciences Beijing China

Symbolic regression (SR) is a powerful technique for discovering the underlying mathematical expressions from observed data. Inspired by the success of deep learning, recent deep generative SR methods have shown promising results. However, these methods face difficulties in processing high-dimensional problems and learning constants due to the large search space, and they don't scale well to unseen problems. In this work, we propose DYSYMNET, a novel neural-guided Dynamic Symbolic network for SR. Instead of searching for expressions within a large search space, we explore symbolic networks with various structures, guided by reinforcement learning, and optimize them to identify expressions that better-fitting the data. Based on extensive numerical experiments on low-dimensional public standard benchmarks and the well-known SRBench with more variables, DYSYMNET shows clear superiority over several representative baseline models. Open source code is available at https://***/AILWQ/DySymNet. Copyright 2024 by the author(s)

关键词： Deep reinforcement learning

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

RLEPSO:Reinforcement learning based Ensemble particle swarm ...

引用

2021年第四届算法、计算和人工智能国际会议

作者： Shiyuan Yin Yi Liu GuoLiang Gong Huaxiang Lu Wenchang Li Institute of Semiconductors CAS Institute of Semiconductors CAS 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

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 *** 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-theart optimization algorithms. The results show that RLEPSO has better performance and outperforms all compared algorithms.

关键词： Particle Swarm Optimization Reinforcement Learning Policy Gradient

来源：评论

学校读者我要写书评

暂无评论

A local descriptor with physiological characteristic for finger vein recognition

arXiv

引用

arXiv 2020年

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

Local feature descriptors exhibit great superiority in finger vein recognition due to their stability and robustness against local changes in images. However, most of these are methods use general-purpose descriptors that do not consider finger vein-specific features. In this work, we propose a finger vein-specific local feature descriptors based physiological characteristic of finger vein patterns, i.e., histogram of oriented physiological Gabor responses (HOPGR), for finger vein recognition. First, prior of directional characteristic of finger vein patterns is obtained in an unsupervised manner. Then the physiological Gabor filter banks are set up based on the prior information to extracte the physiological responses and orientation. Finally, to make feature has robustness against local changes in images, histogram is generated as output by dividing the image into non-overlapping cells and overlapping blocks. Extensive experimental results on several databases clearly demonstrate that the proposed method outperforms most current state-of-the-art finger vein recognition methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Gabor filters

来源：评论

学校读者我要写书评

暂无评论

Building Efficient CNN Architecture for Offline Handwritten Chinese Character Recognition

arXiv

引用

arXiv 2018年

作者： Li, Zhiyuan Teng, Nanjun Jin, Min Lu, Huaxiang CAS Center for Excellence in Brain Science and Intelligence Technology Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Lab of Artificial Networks Institute of Semiconductors CAS University of Chinese Academy of Sciences

Deep convolutional neural networks based methods have brought great breakthrough in images classification, which provides an end-to-end solution for handwritten Chinese character recognition(HCCR) problem through learning discriminative features automatically. Nevertheless, state-of-the-art CNNs appear to incur huge computation cost, and require the storage of a large number of parameters especially in fully connected layers, which is difficult to deploy such networks into alternative hardware devices with limited computation amount. To solve the storage problem, we propose a novel technique called Global Weighted Arverage Pooling for reducing the parameters in fully connected layer without loss in accuracy. Besides, we implement a cascaded model in single CNN by adding mid output layer to complete recognition as early as possible, which reduces average inference time significantly. Experiments were performed on the ICDAR-2013 offline HCCR dataset, and it is found that our proposed approach only needs 6.9ms for classfying a chracter image on average, and achieves the state-of-the-art accuracy of 97.1% while requires only 3.3MB for storage. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Feedback Cancellation Algorithm for Hearing Aids

Design and Implementation of Feedback Cancellation Algorithm...

引用

High Performance Big Data and intelligent Systems (HPBD&IS)

作者： Yuyan Lan Ang Wang Weixin Zhou Wan’ang Xiao Institute of Semiconductors Chinese Academy of Sciences Beijing China School of Microelectronics University of Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China

ISBN: (纸本)9781665413282

This paper presents the optimization idea, hardware implementation architecture and low power optimization process of feedback cancellation algorithm applied in hearing aid chip. Based on the NLMS algorithm, three band limited IIR filters with configurable coefficients are added. Also, the filtered de echo signal is introduced into the calculation of normalized adaptive step factor to solve the biased estimation and distortion problems of NLMS algorithm, so as to realize the accurate adaptation of echo path and echo signal. In the implementation of hardware architecture, the adaptive feedback cancellation module is integrated outside the buffer, and processed point-by-point to reduce the algorithm complexity, hardware implementation resources and power consumption. The solution of double operation unit is further proposed, which improves the efficiency of data processing, and meets the operation requirements at low working frequency. Finally, the MPW chip is verified by SMIC 130nm 1P8M mixed signal CMOS process. Under the working frequency of 4.096MHz, the post simulation power consumption of the module is only 187μW. The chip area is 0.237mm 2 , which fully meets the requirements of low power consumption of hearing aid chip.

关键词： Power demand Echo cancellers Estimation IIR filters Filtering algorithms Hearing aids Distortion

来源：评论

学校读者我要写书评

暂无评论

A Modeling Method for Face Image Deblurring

A Modeling Method for Face Image Deblurring

引用

High Performance Big Data and intelligent Systems (HPBD&IS)

作者： Hao Tian Linjun Sun Xiaoli Dong Baoli Lu Hong Qin Liping Zhang Weijun Li Chinese Academy of Sciences Institute of Semiconductors 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

ISBN: (纸本)9781665413282

This paper aims to learn a face representation that can accurately reconstruct a clear face from a blurred face image. To this end, we propose an explicit model (ID-Face) to represent the human face as a concise expression, which is the sum of a series of analytic function units. And we also design a network, which we named it ID-Net, to train the model. ID-Net consists of two sub-networks with encoder-decoder structure: the encoder of one of the sub-networks learns a set of implicit variables, and the corresponding decoder decodes the implicit variables into the representation’s parameters, which are used to reconstruct the main structure and texture features of the face image. The other sub-network is a general autoencoder to restore the facial details and high frequency parts of the blurred image. Experiments on two kinds of blurred face images show that our method can effectively restore clear and lifelike human face.

关键词： Deep learning Analytical models Image restoration Decoding High frequency Faces Image reconstruction

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：