检索结果-内蒙古大学图书馆

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

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

TRANSFORMER-BASED MODEL FOR SYMBOLIC REGRESSION VIA JOINT SUPERVISED LEARNING 11

TRANSFORMER-BASED MODEL FOR SYMBOLIC REGRESSION VIA JOINT SU...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Li, Wenqiang Li, Weijun Sun, Linjun Wu, Min Yu, Lina Liu, Jingyi Li, Yanjie Tian, Songsong Institute of Semiconductors Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China 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

Symbolic regression (SR) is an important technique for discovering hidden mathematical expressions from observed ***-based approaches have been widely used for machine translation due to their high performance, and are recently highly expected to be used for *** input the data points, then output the expression skeleton, and finally optimize the ***, recent transformer-based methods for SR focus more attention on large scale training data and ignore the ill-posed problem: the lack of sufficient supervision, i.e., expressions that may be completely different have the same supervision because of their same skeleton, which makes it challenging to deal with data that may be from the same expression skeleton but with different ***, we present a transformer-based model for SR with the ability to alleviate this ***, we leverage a feature extractor based on pure residual MLP networks to obtain more information about data ***, the core idea is that we propose a joint learning mechanism combining supervised contrastive learning, which makes features of data points from expressions with the same skeleton more similar so as to effectively alleviates the ill-posed *** benchmark results show that the proposed method is up to 25% higher with respect to the recovery rate of skeletons than typical transformer-based ***, our method outperforms state-of-the-art SR methods based on reinforcement learning and genetic programming in terms of the coefficient of determination (R2). © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Fitting Curves with Fractional Implicit Polynomials: A PSO-Assisted Monomial Combination Optimization Framework 7

Fitting Curves with Fractional Implicit Polynomials: A PSO-A...

引用

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

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

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

Conditional generative adversarial networks based on the principle of homologycontinuity for face aging

Conditional generative adversarial networks based on the pri...

引用

作者： Ning, Xin Gou, Duoduo Dong, Xiaoli Tian, Weijuan Yu, Lina Wang, Chuansheng Institute of Semiconductors Chinese Academy of Sciences Beijing China Cognitive Computing Technology Joint Laboratory Wave Group 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 Shenzhen Institutes of Advanced Technology Chinese Academy of Science Shen Zhen China

Age is one of the most important biological characteristics of the human face. The increase of age coincides with the increase of the aging degree of the face. Face aging synthesis is attracting increasingly more attention from domestic and overseas scholars in the computer vision and computer graphics fields, and it can be integrated into the basic research of face correlation, such as cross-age face analysis and age estimation. At present, some achievements have been made in face aging synthesis research;however, it is still an urgent problem to reduce the number of parameters and computational complexity of the network while ensuring the aging effect. Therefore, a new face aging algorithm is proposed in this article. Unlike the previous methods of aging process simulation, we introduce an assisted age classification network based on the principle of homology continuity, which is more in line with the human cognition process. After pretraining, the result of age classification is improved, and the pretraining model is then added to the framework of aging face generation for fine-tuning to constrain the generated aging face, which can improve the aging accuracy of the generated image. Furthermore, we reconstruct the input face by using the age tag of the input face and the synthesized aging face and maintain the identity invariance in the face aging process by minimizing the reconstruction loss. The experimental results show that the method proposed in this article produces a considerable effect of face aging and significantly reduces the number of parameters and the complexity of computational. © 2020 John Wiley & Sons, Ltd.

关键词： Generative adversarial networks

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

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

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

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：