检索结果-内蒙古大学图书馆

IEEE Silicon Nanoelectronics Workshop (SNW)

作者： Nazek El-Atab Bashayr Alqahtani Program of Electrical and Computer Engineering Computer Electrical Mathematical Sciences and Engineering King Abdullah University of Science and Technology Thuwal Saudi Arabia

Germanium selenide (GeSe) is a highly promising material with several attractive characteristics, particularly in the field of ferroelectric and phase-change memories due to its outstanding electronic behavior. However, the potential of GeSe as a charge-trapping layer in flash memory has received less attention. Herein, the fabrication of a nonvolatile MOS memory device using GeSe nanosheets as a charge-trapping layer was demonstrated and the materials flakes were examined extensively. The electrical performance of the memory device was investigated. Intriguingly, it exhibited an extraordinarily wide memory window of 9 V under ±10 V electrical biasing. Additionally, the devices presented high endurance of $10^{4}$ programming and erasing cycles, and reliable charge storage of only 56% loss after 10 years.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Pulse Width Modulation-Based Spike Generator to Eliminate Timing Errors in Spiking Neural Networks

A Pulse Width Modulation-Based Spike Generator to Eliminate ...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Jungkook Jo Keonhee Sim Sangwoong Sim Jaehoon Jun dept. of electrical and computer engineering and program in semiconductor convergence Inha University Incheon Republic of Korea dept. of electrical engineering Inha University Incheon Republic of Korea

ISBN: (数字)9798331510756

ISBN: (纸本)9798331510763

This paper proposes a novel spike generator for processing in memory (PIM) technology. Most of the electronics today utilize a von Neumann architecture. The von Neumann architecture suffers from the separation of memory and processor. This architecture delays data transfer between memory and processor. To overcome the issues, we utilize the spiking neural network (SNN) that combines memory and processor. SNN can be classified into voltage-based, current-based, and time-based architectures, each with its own pros and cons. Time-based SNN suffers from timing issues. To address the timing sensitivity of time-based neuron SNN, this paper proposes a PWM-based SNN. The PWM-based SNN utilizes pulse width-based logic to overcome timing sensitivity.

关键词： Sensitivity Image edge detection Neurons Spiking neural networks Data transfer Generators Delays Logic Next generation networking Clocks

来源：评论

学校读者我要写书评

暂无评论

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP

Semantic Token Reweighting for Interpretable and Controllabl...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kim, Eunji Shim, Kyuhong Chang, Simyung Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Qualcomm AI Research an initiative of Qualcomm Technologies Inc. Qualcomm Korea YH Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

ISBN: (纸本)9798891761681

A text encoder within Vision-Language Models (VLMs) like CLIP plays a crucial role in translating textual input into an embedding space shared with images, thereby facilitating the interpretative analysis of vision tasks through natural language. Despite the varying significance of different textual elements within a sentence depending on the context, efforts to account for variation of importance in constructing text embeddings have been lacking. We propose a framework of Semantic Token Reweighting to build Interpretable text embeddings (SToRI), which incorporates controllability as well. SToRI refines the text encoding process in CLIP by differentially weighting semantic elements based on contextual importance, enabling finer control over emphasis responsive to data-driven insights and user preferences. The efficacy of SToRI is demonstrated through comprehensive experiments on few-shot image classification and image retrieval tailored to user preferences. © 2024 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

On the Impact of Knowledge Distillation for Model Interpretability 40

On the Impact of Knowledge Distillation for Model Interpreta...

引用

40th International Conference on Machine Learning, ICML 2023

作者： Han, Hyeongrok Siwon, Kim Choi, Hyun-Soo Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of ZIOVISION Inc. Chuncheon Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Several recent studies have elucidated why knowledge distillation (KD) improves model performance. However, few have researched the other advantages of KD in addition to its improving model performance. In this study, we have attempted to show that KD enhances the interpretability as well as the accuracy of models. We measured the number of concept detectors identified in network dissection for a quantitative comparison of model interpretability. We attributed the improvement in interpretability to the class-similarity information transferred from the teacher to student models. First, we confirmed the transfer of class-similarity information from the teacher to student model via logit distillation. Then, we analyzed how class-similarity information affects model interpretability in terms of its presence or absence and degree of similarity information. We conducted various quantitative and qualitative experiments and examined the results on different datasets, different KD methods, and according to different measures of interpretability. Our research showed that KD models by large models could be used more reliably in various fields. The code is available at https://***/Rok07/KD_***. © 2023 Proceedings of Machine Learning Research. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

MODELING THE HODGKIN-HUXLEY NEURON TO DETERMINE NEURONAL ENERGY CONSUMPTION EFFICIENCY AND OXYGEN CONSUMPTION VALUES

Biomedical Sciences Instrumentation

引用

Biomedical Sciences Instrumentation 2022年第2期58卷 50-58页

作者： Enochson, Avery Ewert, Daniel Mitar, Dipankar Striker, Ryan Cleveland, Jerika Wolf, Henry Gieser, Anna Braaten, Ben Allen, Jeffery Allen, Monica Department of Integrated Engineering at Iron Range Engineering Program of Minnesota State University Mankato MN United States Department of Computer Science and Computer Engineering University of Wisconsin – La Crosse La CrosseWI United States Department of Electrical and Computer Engineering North Dakota State University FargoND United States Air Force Research Laboratory Munitions Directorate Eglin Air Force Base Eglin AFB FL United States

Understanding neuronal structure and function is essential to studying the human brain. The goal of this project was to create a model of human brain neurons that accurately reflects neuronal function, energy consumption, and oxygen consumption. Extensive work has been performed on the Hodgkin-Huxley model of neurons to accurately model neuronal firing. This study focuses on the creation of a model of the Hodgkin-Huxley neuron in MATLAB with the assistance of the DynaSim toolbox. This model was used to compute values and using another model the energy efficiency of the neuron was calculated and related to oxygen consumption, which then corresponds to Blood Oxygenation Level Dependent (BOLD) imaging in fMRI. The results of this study provide detailed visual and technical information about how the brain neurons function, which is crucial to the further development in brain imaging techniques and to further our understanding of why and how our complex brains function. © 2022 IAE All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Automated Image Captioning with Multi-layer Gated Recurrent Unit 30

Automated Image Captioning with Multi-layer Gated Recurrent ...

引用

30th European Signal Processing Conference, EUSIPCO 2022

作者： Moral, Özge Taylan Kiliç, Volkan Onan, Aytug Wang, Wenwu Electrical and Electronics Engineering Graduate Program Izmir Katip Celebi University Turkey Department of Computer Engineering Izmir Katip Celebi University Turkey University of Surrey United Kingdom

ISBN: (纸本)9789082797091

Describing the semantic content of an image via natural language, known as image captioning, has recently attracted substantial interest in computer vision and language processing communities. Current image captioning approaches are mainly based on an encoder-decoder framework in which visual information is extracted by an image encoder and captions are generated by a text decoder, using convolution neural networks (CNN) and recurrent neural networks (RNN), respectively. Although this framework is promising for image captioning, it has limitations in utilizing the encoded visual information for generating grammatically and semantically correct captions in the RNN decoder. More specifically, the RNN decoder is ineffective in using the contextual information from the encoded data due to its limited ability in capturing long-term complex dependencies. Inspired by the advantage of gated recurrent unit (GRU), in this paper, we propose an extension of conventional RNN by introducing a multi-layer GRU that modulates the most relevant information inside the unit to enhance the semantic coherence of captions. Experimental results on the MSCOCO dataset show the superiority of our proposed approach over the state-of-the-art approaches in several performance metrics. © 2022 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Auxiliary Classifier based Residual RNN for Image Captioning 30

Auxiliary Classifier based Residual RNN for Image Captioning

引用

30th European Signal Processing Conference, EUSIPCO 2022

作者： Çayli, Özkan Kiliç, Volkan Onan, Aytug Wang, Wenwu Electrical and Electronics Engineering Graduate Program Izmir Katip Çelebi University Turkey Department of Computer Engineering Izmir Katip Çelebi University Turkey University of Surrey United Kingdom

ISBN: (纸本)9789082797091

Image captioning aims to generate a description of visual contents with natural language automatically. This is useful in several potential applications, such as image understanding and virtual assistants. With recent advances in deep neural networks, natural and semantic text generation has been improved in image captioning. However, maintaining the gradient flow between neurons in consecutive layers becomes challenging as the network gets deeper. In this paper, we propose to integrate an auxiliary classifier in the residual recurrent neural network, which enables the gradient flow to reach the bottom layers for enhanced caption generation. Experiments on the MSCOCO and VizWiz datasets demonstrate the advantage of our proposed approach over the state-of-the-art approaches in several performance metrics. © 2022 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and Optimization of the Porous Metamaterial EM Absorbers in X-band

Design and Optimization of the Porous Metamaterial EM Absorb...

引用

2023 IEEE Symposium on Electromagnetic Compatibility and Signal/Power Integrity, EMC+SIPI 2023

作者： Anurakparadorn, Kanat Taub, Alan Michielssen, Eric University of Michigan Macromolecular Science and Engineering Program Department of Material Science and Engineering Ann ArborMI United States University of Michigan Department of Mechanical Engineering Ann ArborMI United States University of Michigan Department of Electrical Engineering and Computer Science Ann ArborMI United States

ISBN: (纸本)9798350309768

A strategy that combines experiment and simulation to design and optimize electromagnetic (EM) metamaterial absorbers containing a periodic porous structure is described. The approach provides the ability to produce absorbers that meet multiple user-specified objectives. Using the measured intrinsic properties of the baseline materials as an input to EM-field based computational modelling and optimization, absorption by the studied metamaterials measured by their reflection loss (RL) increases significantly. The resulting metamaterials have the potential for lower cost and lighter weight while providing greater protection than traditional metal gaskets and foams. © 2023 IEEE.

关键词： Metamaterials

来源：评论

学校读者我要写书评

暂无评论

Normality Addition via Normality Detection in Industrial Image Anomaly Detection Models

arXiv

引用

arXiv 2024年

作者： Yi, Jihun Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of School of Computer Science and Engineering Soongsil University Seoul Korea Republic of Department of Electrical and Computer Engineering and Interdisciplinary Program in AI Seoul National University Seoul Korea Republic of

The task of image anomaly detection (IAD) aims to identify deviations from normality in image data. These anomalies are patterns that deviate significantly from what the IAD model has learned from the data during training. However, in real-world scenarios, the criteria for what constitutes normality often change, necessitating the reclassification of previously anomalous instances as normal. To address this challenge, we propose a new scenario termed "normality addition," involving the post-training adjustment of decision boundaries to incorporate new normalities. To address this challenge, we propose a method called Normality Addition via Normality Detection (NAND), leveraging a vision-language model. NAND performs normality detection which detect patterns related to the intended normality within images based on textual descriptions. We then modify the results of a pre-trained IAD model to implement this normality addition. Using the benchmark dataset in IAD, MVTec AD, we establish an evaluation protocol for the normality addition task and empirically demonstrate the effectiveness of the NAND method. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Low-rank variational Bayes correction to the Laplace method

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 3032-3056页

作者： Janet Van Niekerk Håvard Rue Statistics Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal Kingdom of Saudi Arabia

Approximate inference methods like the Laplace method, Laplace approximations and variational methods, amongst others, are popular methods when exact inference is not feasible due to the complexity of the model or the abundance of data. In this paper we propose a hybrid approximate method called Low-Rank Variational Bayes correction (VBC), that uses the Laplace method and subsequently a Variational Bayes correction in a lower dimension, to the joint posterior mean. The cost is essentially that of the Laplace method which ensures scalability of the method, in both model complexity and data size. Models with fixed and unknown hyperparameters are considered, for simulated and real examples, for small and large data sets.

关键词： information processing rule INLA Laplace LGM variational Bayes

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：