检索结果-内蒙古大学图书馆

Neuromorphic Systems (ICONS), International Conference on

作者： Mark Schöne Neeraj Mohan Sushma Jingyue Zhuge Christian Mayr Anand Subramoney David Kappel Chair of Highly-Parallel VLSI-Systems and Neuro-Microelectronics TU Dresden Dresden Germany Ruhr University Bochum Institut für Neuroinformatik Germany Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) TU Dresden Dresden Germany Centre for Tactile Internet (CeTI) with Human-in-the-Loop TU Dresden Dresden Germany Dept. of Computer Science Royal Holloway University of London Egham United Kingdom

ISBN: (数字)9798350368659

ISBN: (纸本)9798350368666

Event-based sensors feature valuable properties for real-time processing such as fast response times and encoding of the sensory data as successive temporal differences. However, most current methods either collapse events into frames, therefore suppressing these properties, or cannot scale up when processing the event data directly event-by-event. In this work, we address the key challenges of scaling up event-by-event modeling of the long event streams emitted by such sensors, which is a particularly relevant problem for neuromorphic computing. While prior methods can process up to a few thousand time steps, our model, based on modern recurrent deep state-space models, scales to event streams of millions of events for both training and inference. We leverage their stable parameterization for learning long-range dependencies, parallelizability along the sequence dimension, and their ability to integrate asynchronous events effectively to scale them up to long event streams. We further augment these with novel event-centric techniques enabling our model to match or beat the state-of-the-art performance on several event stream benchmarks. In the Spiking Speech Commands task, we improve state-of-the-art by a large margin of 7.7 % to 88.4 %. On the DVS128-Gestures dataset, we achieve competitive results without using frames or convolutional neural networks. Our work demonstrates, for the first time, that it is possible to use fully event-based processing with purely recurrent networks to achieve state-of-the-art task performance in several event-based benchmarks.

关键词： Training Event detection Computational modeling Benchmark testing Sensor systems Real-time systems Sensors State-space methods Time factors Streams

来源：评论

学校读者我要写书评

暂无评论

Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning

arXiv

引用

arXiv 2023年

作者： Zhai, Shengfang Dong, Yinpeng Shen, Qingni Pu, Shi Fang, Yuejian Su, Hang School of Software and Microelectronics Peking University China Department of Computer Science & Technology Tsinghua University China ShengShu Beijing China School of Software and Microelectronics National Engineering Research Center for Software Engineering PKU-OCTA Laboratory for Blockchain and Privacy Computing Peking University Beijing100871 China Dept. of Comp. Sci. and Tech. Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Beijing100084 China

With the help of conditioning mechanisms, the state-of-the-art diffusion models have achieved tremendous success in guided image generation, particularly in text-to-image synthesis. To gain a better understanding of the training process and potential risks of text-to-image synthesis, we perform a systematic investigation of backdoor attack on text-to-image diffusion models and propose BadT2I, a general multimodal backdoor attack framework that tampers with image synthesis in diverse semantic levels. Specifically, we perform backdoor attacks on three levels of the vision semantics: Pixel-Backdoor, Object-Backdoor and Style-Backdoor. By utilizing a regularization loss, our methods efficiently inject backdoors into a large-scale text-to-image diffusion model while preserving its utility with benign inputs. We conduct empirical experiments on Stable Diffusion, the widely-used text-to-image diffusion model, demonstrating that the large-scale diffusion model can be easily backdoored within a few fine-tuning steps. We conduct additional experiments to explore the impact of different types of textual triggers, as well as the backdoor persistence during further training, providing insights for the development of backdoor defense methods. Besides, our investigation may contribute to the copyright protection of text-to-image models in the future. Our Code: https://***/sf-zhai/BadT2I. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous CFET: A Pathway to CMOS Performance Balance Engineering

Heterogeneous CFET: A Pathway to CMOS Performance Balance En...

引用

IEEE Silicon Nanoelectronics Workshop (SNW)

作者： Xin-Ren Yu Wen-Hsiang Lu Shu-Wei Chang Wen-Hsin Chang Darsen D. Lu Yao-Jen Lee Tatsuro Maeda Wen-Fa Wu Yi-Ming Li Yeong-Her Wang Inst. of Microelectronics Natl. Cheng Kung University Tainan Taiwan Dept. of Electrical Engineering Natl. Cheng Kung University Tainan Taiwan National Institute of Advanced Industrial Science and Technology (AIST) Tsukuba Japan Inst. of Pioneer Semiconductor Innovation National Yang Ming Chiao Tung University Hsinchu Taiwan Taiwan Semiconductor Research Inst. (TSRI) Hsinchu Taiwan College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

The CFETs can provide high-performance characteristics with significant area reduction for Å technology nodes. However, mobilities between n/p FETs need to be considered for the performance balance of CMOS. This ... 详细信息

ISBN: (数字)9798350391633

ISBN: (纸本)9798350391640

关键词： Wafer bonding Conferences Field effect transistors Silicon Nanoelectronics

来源：评论

学校读者我要写书评

暂无评论

Finding a Largest-Area Triangle in a Terrain in Near-Linear Time

arXiv

引用

arXiv 2021年

作者： Cabello, Sergio Das, Arun Kumar Das, Sandip Mukherjee, Joydeep Faculty of Mathematics and Physics University of Ljubljana Slovenia Institute of Mathematics Physics and Mechanics Slovenia Advanced Computing and Microelectronics Unit Indian Statistical Institute India Dept. of Computer Science Ramakrishna Mission Vivekananda Educational and Research Institute India

A terrain is an x-monotone polygon whose lower boundary is a single line segment. We present an algorithm to find in a terrain a triangle of largest area in O(n log n) time, where n is the number of vertices defining the terrain. The best previous algorithm for this problem has a running time of O(n2). Copyright © 2021, The Authors. All rights reserved.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Neural architecture search under black-box objectives with deep reinforcement learning and increasingly-sparse rewards 2

Neural architecture search under black-box objectives with d...

引用

2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020

作者： Alioscha-Perez, Mitchel Berenguer, Abel Diaz Pei, Ercheng Oveneke, Meshia Cedric Sahli, Hichem Vrije Universiteit Brussel VUB-NPU Joint AVSP Lab Electronics and Informatics Dept. Brussels1050 Belgium Northwestern Polytechnical University School of Computer Science VUB-NPU Joint AVSP Lab Xi'an710072 China Interuniv. MicroElectronics Centre Heverlee Belgium

ISBN: (纸本)9781728149851

In this paper, we address the problem of neural architecture search (NAS) in a context where the optimality policy is driven by a black-box Oracle \mathcal{O} with unknown form and derivatives. In this scenario, \mathcal{O}(A-{C}) typically provides readings from a set of sensors on how a neural network architecture A-{C} fares in a target hardware, including its: power consumption, working temperature, \mathbf{cpu}/\mathbf{gpu} usage, central bus occupancy, and more. Current differentiable NAS approaches fail in this problem context due to lack of access to derivatives, whereas traditional reinforcement learning NAS approaches remain too expensive computationally. As solution, we propose a reinforcement learning NAS strategy based on policy gradient with increasingly sparse rewards. We rely on the fact [1] that one does not need to fully train the weights of two neural networks to compare them. Our solution starts by comparing architecture candidates with almost fixed weights and no training, and progressively shifts toward comparisons under full weights training. Experimental results confirmed both the accuracy and training efficiency of our solution, as well as its compliance with soft/hard constraints imposed on the sensors feedback. Our strategy allows finding near-optimal architectures significantly faster, in approximately 1/3 of the time it would take otherwise. © 2020 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DOA estimation for transmit beamspace MIMO radar via tensor decomposition with Vandermonde factor matrix

arXiv

引用

arXiv 2021年

作者： Xu, Feng Morency, Matthew W. Vorobyov, Sergiy A. School of Information and Electronics Beijing Institute of Technology Beijing100081 China Department of Signal Processing and Acoustics Aalto University Espoo02150 Finland Dept. Microelectronics School of Electrical Engineering Mathematics and Computer Science Delft University of Technology Mekelweg 4 Delft2628 CD Netherlands

We address the problem of tensor decomposition in application to direction-of-arrival (DOA) estimation for transmit beamspace (TB) multiple-input multiple-output (MIMO) radar. A general 4-order tensor model that enables computationally efficient DOA estimation is designed. Whereas other tensor decomposition-based methods treat all factor matrices as arbitrary, the essence of the proposed DOA estimation method is to fully exploit the Vandermonde structure of the factor matrices to take advantage of the shift-invariance between and within different subarrays. Specifically, the received signal of TB MIMO radar is expressed as a 4-order tensor. Depending on the target Doppler shifts, the constructed tensor is reshaped into two distinct 3-order tensors. A computationally efficient tensor decomposition method is proposed to decompose the Vandermonde factor matrices. The generators of the Vandermonde factor matrices are computed to estimate the phase rotations between subarrays, which can be utilized as a look-up table for finding target DOA. It is further shown that our proposed method can be used in a more general scenario where the subarray structures can be arbitrary but identical. The proposed DOA estimation method requires no prior information about the tensor rank and is guaranteed to achieve precise decomposition result. Simulation results illustrate the performance improvement of the proposed DOA estimation method as compared to conventional DOA estimation techniques for TB MIMO Radar. © 2021, CC0.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Concept of an Electronic Device Dedicated to Imbalance Disorders Monitoring

Concept of an Electronic Device Dedicated to Imbalance Disor...

引用

International Conference on CAD Systems in microelectronics (CADSM)

作者： Mariusz Jankowski Michal Szermer Piotr Amrozik Dept. of Microelectronics and Computer Science Lodz University of Technology Lodz Poland

In this paper we present the main concept of an electronic device, destined to work as a part of a system devoted to monitoring human gait and movement in daily life. Operation of the device and the whole system is focused on diagnosis of the imbalance disorders, especially in elderly persons. This small electronic device is intended to be worn by the monitored person in non-restraining and comfortable manner. The data collected by the device are to be sent to accompanying data processing unit in form of e.g. a smartphone. After initial processing, the obtained data are then sent to a medical center for raising alert, further processing and storage. The paper is focused on design of a microelectromechanical system (MEMS) and an application-specific integrated circuit (ASIC) responsible for gathering, conditioning and conversion of the data into digital form best suited for quantitative analysis and transmission.

关键词： Micromechanical devices Biomedical monitoring Accelerometers Monitoring Sensors Medical diagnostic imaging Software

来源：评论

学校读者我要写书评

暂无评论

Simulations and analysis of MEMS vibrating gyroscope with geometry details in Matlab/SIMULINK environment

Simulations and analysis of MEMS vibrating gyroscope with ge...

引用

2018 Baltic URSI Symposium, URSI 2018

作者： Nazdrowicz, Jacek Szermer, Michal Amrozik, Piotr Napieralski, Andrzej Dept. of Microelectronics and Computer Science Lodz University of Technology 221/223 Wolczanska St Lodz90-924 Poland

ISBN: (纸本)9788394942137

This paper presents the mathematical model of the MEMS gyroscope implemented in the Matlab/SIMULINK package. This model was developed with particular emphasis on spring geometry, which plays a key role. Their shape strongly affects the eigenfrequencies of the structure. The paper focuses on the output characteristics of the gyroscope in sense directions showing maximum displacement dependency at different geometry dimensions. © 2018 Warsaw University of Technology.

关键词： Simulink

来源：评论

学校读者我要写书评

暂无评论

Different methods of capacitive comb drive MEMS accelerometer simulations

Different methods of capacitive comb drive MEMS acceleromete...

引用

2018 Baltic URSI Symposium, URSI 2018

作者： Nazdrowicz, Jacek Szermer, Michal Maj, Cezary Napieralski, Andrzej Dept. of Microelectronics and Computer Science Lodz University of Technology 221/223 Wolczanska St Lodz90-924 Poland

ISBN: (纸本)9788394942137

In this paper there are presented different methods of modeling MEMS accelerometers. Models were designed in Matlab/SIMULINK and COMSOL and then simulations were performed. Based on these simulations results and their accuracy were compared. Authors also take into consideration on some details, which can have impact on final results and possibility to get similar results in both mathematical and Finite Element Method models. The objective of this research work is to present designing and simulation capabilities of MEMS devices with mathematical models and Finite Element Method and present some response results. © 2018 Warsaw University of Technology.

关键词： Simulink

来源：评论

学校读者我要写书评

暂无评论

Different methods of capacitive comb drive MEMS accelerometer simulations

Different methods of capacitive comb drive MEMS acceleromete...

引用

Baltic URSI Symposium (URSI)

作者： Jacek Nazdrowicz Michał Szermer Cezary Maj Andrzej Napieralski Dept. of Microelectronics and Computer Science Lodz University of Technology Lodz Poland

关键词： Mathematical model Accelerometers Springs Integrated circuit modeling Micromechanical devices Finite element analysis Software packages

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：