检索结果-内蒙古大学图书馆

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

Novel activation function with pixelwise modeling capacity for lightweight neural network design

Novel activation function with pixelwise modeling capacity f...

引用

作者： Liu, Yi Guo, Xiaozhou Tan, Kaijun Gong, Guoliang Lu, Huaxiang Lab of Artificial Networks Institute of Semiconductors Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China

The development of lightweight networks makes neural networks more efficient to be widely applied to various tasks. Considering the deployment of hardware like edge devices and mobile phones, we prioritize lightweight networks. However, their accuracy has always lagged far behind SOTA networks. In this article, we present a simple yet effective activation function, called WReLU, to improve the performance of lightweight networks significantly by adding a residual spatial condition. Moreover, we use a strategy to switch activation functions after determining which convolutional layer to use. We perform experiments on ImageNet 2012 classification dataset in CPU, GPU, and edge devices. Experiments demonstrate that WReLU improves the accuracy of classification significantly. Meanwhile, our strategy balances the effect of additional parameters and multiply accumulate. Our method improves the accuracy of SqueezeNet and SqueezeNext by more than 5% without increasing extensive parameters and computation. For the lightweight network with a large number of parameters, such as MobileNet and ShuffleNet, there is also a significant improvement. Additionally, the inference speed of most lightweight networks using our WReLU strategy is almost the same as the baseline model on different platforms. Our approach not only ensures the practicability of the lightweight network but also improves its performance. © 2021 John Wiley & Sons Ltd.

关键词： Classification (of information)

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 hardware-friendly low-bit post-training quantization algorithm for lightweight networks

TechRxiv

引用

TechRxiv 2023年

作者： Li, Jixing Zhao, Zhiyuan Chen, Gang Jin, Ming Lu, Huaxiang Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China University of Chinese Academy of Sciences Beijing100089 China Beijing Key Lab of Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing100083 China

Lightweight convolutional neural networks (LCNNs) are commonly quantized and deployed on edge devices to fulfill the requirements of low-power, high-performance tasks. Utilizing uniform, symmetric, per-tensor quantization with power-of-two scale factors can enhance hardware efficiency, albeit at the cost of significant accuracy degradation. In this work, we present a hardware-friendly post-training quantization (HFPTQ) framework to address this problem. HFPTQ employs a synergistic combination of established techniques, including Cross-Layer Equalization (CLE), Absorbing High Bias (AHB), and Adaptive Rounding. Furthermore, HFPTQ introduces quantization-aware equalization by optimizing the equalization scale and absorption vector to minimize block reconstruction error and network prediction difference. Additionally, HFPTQ introduces an adaptive bias correction mechanism. While optimizing weight rounding, bias term is co-optimized to rectify the mean shift in activations induced by quantization. Experimental results, based on the ImageNet dataset, demonstrate that HFPTQ significantly enhances the low-bit hardware-friendly quantization performance of lightweight networks. © 2023, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Blind separation of noncooperative paired carrier multiple access signals based on improved quantum-inspired evolutionary algorithm and receding horizon optimization

Blind separation of noncooperative paired carrier multiple a...

引用

作者： Deng, Qi Zhang, Shanshan Chen, Gang Lu, Huaxiang Lab of Artificial Networks Institute of Semiconductors CAS Beijing China University of Chinese Academy of Sciences Beijing China CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China

The single-channel blind source separation of paired carrier multiple access (PCMA) signal is a key technology in satellite communications. Due to the high-order complexity of existing separation methods and the uncertainty of channel parameters, the processing of noncooperative PCMA signals with long memory remains a great challenge. In this article, the blind separation was solved as the joint channel estimation and sequence detection, and a novel blind separation algorithm based on the improved quantum-inspired evolutionary algorithm (IQEA) and receding horizon optimization was proposed. Considering the practical scenarios, a mixed PCMA signal model with noninteger period sampling was presented in advance. Combined with the proposed signal model, the IQEA was applied to recover the uplink signals from the mixed PCMA signals by its iterative estimation. Meanwhile, to reduce the computational complexity caused by long memory of PCMA signals, the receding horizon optimization was introduced to process the whole signal sequence as a dynamic programming problem. The simulation results verified that the proposed RH-IQEA outperforms existing state-of-the-art separation algorithms in the blind separation of noncooperative PCMA signals, with higher accuracy, lower-order complexity and stronger robustness to parameter estimation errors. © 2021 John Wiley & Sons, Ltd.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Search-based Ordered Password Generation of Autoregressive neural networks

arXiv

引用

arXiv 2024年

作者： Jin, Min Ye, Junbin Shen, Rongxuan Lu, Huaxing 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 Beijing100049 China Beijing Key Lab of Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing100083 China

Passwords are the most widely used method of authentication and password guessing is the essential part of password cracking and password security research. The progress of deep learning technology provides a promising way to improve the efficiency of password guessing. However, current research on neural network password guessing methods mostly focuses on model structure and has overlooked the generation method. Due to the randomness of sampling, not only the generated passwords have a large number of duplicates, but also the order in which passwords generated is random, leading to inefficient password attacks. In this paper, we propose SOPG, a search-based ordered password generation method, which enables the password guessing model based on autoregressive neural network to generate passwords in approximately descending order of probability. Experiment on comparison of SOPG and Random sampling shows passwords generated by SOPG do not repeat, and when they reach the same cover rate, SOPG requires fewer inferences and far fewer generated passwords than Random sampling, which brings great efficiency improvement to subsequent password attacks. We build SOPGesGPT, a password guessing model based on GPT, using SOPG to generate passwords. Compared with the most influential models OMEN, FLA, PassGAN, VAEPass and the latest model PassGPT in one-site test, experiments show that SOPGesGPT is far ahead in terms of both effective rate and cover rate. As to cover rate that everyone recognizes, SOPGesGPT reaches 35.06%, which is 254%, 298%, 421%, 380%, 81% higher than OMEN, FLA, PassGAN, VAEPass, and PassGPT respectively. © 2024, CC BY.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

An FPGA-Based High-Throughput Dataflow Accelerator for Lightweight neural network

An FPGA-Based High-Throughput Dataflow Accelerator for Light...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Zhiyuan Zhao Jixing Li Gang Chen Zhelong Jiang Ruixiu Qiao Peng Xu Yihao Chen Huaxiang Lu School of Microelectronics University of Science and Technology of China Hefei China Institute of Semiconductors Chinese Academy of Sciences Beijing China Materials and Optoelectronics Research Center University of Chinese Academy of Sciences Beijing China College of Microelectronics University of Chinese Academy of Sciences Beijing China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Laboratory Beijing China

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

Lightweight neural networks (LWNNs) have drawn significant attention recently for compact architecture and acceptable accuracy. Despite achieving substantial reductions in computation complexity and model size, increased memory access demands are caused by the extensive use of depthwise separable convolutions (DSCs) and skip-connection blocks (SCBs), which makes it difficult to achieve the anticipated performance. To process LWNNs efficiently, an FPGA-based dataflow accelerator is proposed in this paper. Firstly, a pixel-based streaming strategy is introduced to reduce off-chip memory access while minimizing on-chip memory overhead. Furthermore, an adaptive bandwidth computing engine (CE) is designed to increase computational efficiency in multi-CE architecture. Finally, based on the scalable CE, a dynamic parallelism allocation algorithm is proposed to avoid underutilization of on-chip computing resources. Shuf-fleNetV2 is implemented on Xilinx ZC706 platform, and the results show the proposed accelerator can achieve a state-of-the-art performance of 1771.2 FPS and computational efficiency of 0.64 GOPS/DSP, which is 5.3× of the reference design.

关键词： Performance evaluation Heuristic algorithms neural networks Bandwidth Computer architecture Parallel processing Computational efficiency

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

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：