检索结果-内蒙古大学图书馆

2021 Conference on Artificial Life, ALIFE 2021

作者： Leite, Abe Izquierdo, Eduardo J. Cognitive Science Program Indiana University Bloomington United States Luddy School of Informatics Computing and Engineering Indiana University Bloomington United States

In order to make lifelike, versatile learning adaptive in the artificial domain, one needs a very diverse set of behaviors to learn. We propose a parameterized distribution of classic control-style tasks with minimal information shared between tasks. We discuss what makes a task trivial and offer a basic metric, time in convergence, that measures triviality. We then investigate analytic and empirical approaches to generating reward structures for tasks based on their dynamics in order to minimize triviality. Contrary to our expectations, populations evolved on reward structures that incentivized the most stable locations in state space spend the least time in convergence as we have defined it, because of the outsized importance our metric assigns to behavior fine-tuning in these contexts. This work paves the way towards an understanding of which task distributions enable the development of learning. © 2021 ALIFE. All Rights Reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

An Assessment of Patent Scoring Using Natural Language programming

An Assessment of Patent Scoring Using Natural Language Progr...

引用

2022 Portland International Conference on Management of engineering and Technology, PICMET 2022

作者： Khongamnuaisak, Lertchai Pentrakoon, Duanghathai Sinthupinyo, Sukree Suanpong, Kwanrat Chulalongkorn University Technopreneurship and Innovation Management Program Graduate School Bangkok Thailand Chulalongkorn University Faculty of Science Department of Materials Science Bangkok Thailand Faculty of Engineering Chulalongkorn University Department of Computer Engineering Bangkok Thailand Chulalongkorn Business School Commerce Department Bangkok Thailand

ISBN: (数字)9781890843410

ISBN: (纸本)9781890843410

Patent has been an increasingly important role in the world because it is not only significant to protect the invention of the company's business but also to generate revenue from the commercialization. WIPO (2018) reports that the repository has many patents so, to assess patent, it consumes time and requires various expertise. Generally, several models have been developed to address this matter, which to assess using a questionnaire tool for portfolios by human. Perhaps, there is not precise because it is assessed base on personal bias or previous experience of expertise. So that, occurs bias any limitation exists that our research will address by artificial intelligence. Thus, this research applies a Natural Language programming to assess for commercial of the patent. Then, the obtained data is used to assigned factors and calculate the model for assessing the commercialization of patent. This finding should deliver an alternative effective patent assessment, which is tool addresses, some current deficiency patent assessment for commercialization. © 2022 PICMET.

关键词： Patents and inventions

来源：评论

学校读者我要写书评

暂无评论

Thermal Hall effect in insulating quantum materials

引用

The Innovation 2022年第5期3卷 3-4页

作者： Shucheng Guo Youming Xu Ran Cheng Jianshi Zhou Xi Chen Department of Electrical and Computer Engineering University of CaliforniaRiversideRiversideCA 92521USA Department of Physics and Astronomy University of CaliforniaRiversideRiversideCA 92521USA Materials Science and Engineering Program Department of Mechanical EngineeringUniversity of Texas at AustinAustinTX 78712USA

The emerging field of quantum materials involves an exciting new class of materials in which charge,spin,orbital,and lattice degrees of freedom are intertwined,exhibiting a plethora of exotic physical *** materials include,but are not limited to,superconductors,topological quantum matter,and systems with frustrated spins,which enable a wide range of potential applications in biomedicine,energy transport and conversion,quantum sensing,and quantum information processing。

关键词： properties. quantum topological

来源：评论

学校读者我要写书评

暂无评论

Cascaded multiparameter quantum metrology

引用

Physical Review A 2025年第1期111卷 012618-012618页

作者： Gregory Krueper Lior Cohen Juliet T. Gopinath Department of Physics University of Colorado Boulder Boulder Colorado 80309 USA Department of Electrical Computer and Energy Engineering University of Colorado Boulder Boulder Colorado 80309 USA Materials Science and Engineering Program University of Colorado Boulder Boulder Colorado 80309 USA

We present an innovative, platform-independent concept for multiparameter sensing where the measurable parameters are in series, or cascaded, enabling measurements as a function of position. With temporally resolved detection, we show that squeezing can give a quantum enhancement in sensitivity over that of classical states by a factor of e2r, where r≈1 is the squeezing parameter. As an example, we have modeled an interferometer that senses multiple phase shifts along the same path, demonstrating a maximal quantum advantage by combining a coherent state with squeezed vacuum. Further classical modeling with up to 100 phases shows linear scaling potential for adding nodes to the sensor. The approach can be applied to remote sensing, geophysical surveying, and infrastructure monitoring.

关键词： Interferometers

来源：评论

学校读者我要写书评

暂无评论

AI for Bias Detection: Investigating the Existence of Racial Bias in Police Killings

AI for Bias Detection: Investigating the Existence of Racial...

引用

2021 IEEE MIT Undergraduate Research Technology Conference, URTC 2021

作者： Somalwar, Anaiy Bansal, Chinmay Lintu, Nathan Shah, Rishab Mui, Phil Aspiring Scholars Directed Research Program Department of Computer Science Engineering FremontCA United States

ISBN: (纸本)9781665405959

A recent paper in the Journal of Politics applied machine learning models to analyze racial disparities in police shooting fatalities. It suggested building generalizable binary classifiers simply based on those social and demographic factors. This recent research in 2019 was not able to establish a convincing machine learning model account for the observed racial bias in fatalities resulting from police shootings. This paper proposes key improvements made from the previous machine learning research through the use of class weights, random oversampling, and a more expansive dataset. We are able to show generalizable relationships between factors related to a police killing and the race of the fatality with over 80 percent accuracy based on the US national police shooting fatality data in recent years. This research suggests areas for further investigations of racial bias in police killings with supervised machine learning as a methodology for algorithmic and data bias detection. © 2021 IEEE.

关键词： Law enforcement

来源：评论

学校读者我要写书评

暂无评论

NiSNN-A: Non-iterative Spiking Neural Networks with Attention with Application to Motor Imagery EEG Classification

arXiv

引用

arXiv 2023年

作者： Zhang, Chuhan Pan, Wei Della Santina, Cosimo Department of Cognitive Robotics Faculty of Mechanical Engineering Delft University of Technology Delft Netherlands Department of Computer Science The University of Manchester Manchester United Kingdom

Motor imagery, an important category in electroencephalogram (EEG) research, often intersects with scenarios demanding low energy consumption, such as portable medical devices and isolated environment operations. Traditional deep learning algorithms, despite their effectiveness, are characterized by significant computational demands accompanied by high energy usage. As an alternative, spiking neural networks (SNNs), inspired by the biological functions of the brain, emerge as a promising energy-efficient solution. However, SNNs typically exhibit lower accuracy than their counterpart convolutional neural networks (CNNs). Although attention mechanisms successfully increase network accuracy by focusing on relevant features, their integration in the SNN framework remains an open question. In this work, we combine the SNN and the attention mechanisms for the EEG classification, aiming to improve precision and reduce energy consumption. To this end, we first propose a Non-iterative Leaky Integrate-and-Fire (NiLIF) neuron model, overcoming the gradient issues in traditional Spiking Neural Networks (SNNs) that use Iterative LIF neurons for long time steps. Then, we introduce the sequence-based attention mechanisms to refine the feature map. We evaluated the proposed Non-iterative SNN with Attention (NiSNN-A) model on two motor imagery EEG datasets, OpenBMI and BCIC IV 2a. Experiment results demonstrate that 1) our model outperforms other SNN models by achieving higher accuracy, 2) our model increases energy efficiency compared to the counterpart CNN models (i.e., by 2.13 times) while maintaining comparable accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Hyperparameter Optimization Using Deep Q-Network and BRKGA

Efficient Hyperparameter Optimization Using Deep Q-Network a...

引用

Congress on Evolutionary Computation

作者： Kosei Kobayashi Masayoshi Aritsugi Pedro Henrique González Israel Mendonça Graduate School of Science and Technology Kumamoto University Kumamoto Japan Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan System Engineering and Computer Science Program Federal University of Rio de Janeiro Rio de Janeiro Brazil

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Hyperparameter optimization (HPO) is paragon to maximize performance when designing machine learning models. Among different HPO methods, Genetic Algorithm (GA) based optimization is considered effective because it allows a wide and diverse range of solutions to be explored. However, GA's exploratory nature makes this type of algorithm to evaluate many solutions that do not improve the overall performance. This is specially costly when the objective function to be evaluated is time-consuming, like in the HPO field. In this paper, we propose an efficient hybrid algorithm that is able to reduce computational cost by combining deep reinforcement learning with the Biased Random Key Genetic Algorithm (BRKGA), a variant of genetic algorithms. Our reinforcement learning agent has a decision-making role during the population's fitness calculation, in which it filters out chromosomes that would not improve the overall fitness of the population. The agent uses small amounts of pre-trained data to identify trends in potentially good solutions, and carry out its decision process. We conduct experiments on eight different datasets to assess the effectiveness of the proposed method, and the results show that the proposed method can significantly reduce the computation time of hyperparameter search using BRKGA (up to 44% reduction in computational time) without compromising the quality of the solution (no statistically difference in results).

关键词： Machine learning algorithms Filters Sociology Evolutionary computation Hyperparameter optimization Market research Linear programming

来源：评论

学校读者我要写书评

暂无评论

Optimization of Node Reduction Using BRKGA for GNN-Based Traffic Speed Forecasting

Optimization of Node Reduction Using BRKGA for GNN-Based Tra...

引用

Congress on Evolutionary Computation

作者： Yuto Inokuchi Pedro Henrique González Israel Mendonça Masayoshi Aritsugi Graduate School of Science and Technology Kumamoto University Kumamoto Japan System Engineering and Computer Science Program Federal University of Rio de Janeiro Rio de Janeiro Brazil Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

While Spatio-Temporal Graph Convolutional Networks (STGCNs) are an effective method for traffic speed fore-casting, their training and inference tend to be time-consuming. In this paper, we aim to refine these networks by strategically reducing their number of nodes, thereby boosting computational efficiency. The nodes in these graphs represent data observed for road segments, and by analyzing the interconnections and layout of the graph, we can identify nodes with minimal contribution to overall performance. Removing these nodes can potentially decrease computation time while maintaining the prediction accuracy. We employ the Biased Random-Key Genetic Algorithm (BRKGA) to identify a good set of nodes for removal, based on a predefined percentage reduction of the original graph size (e.g., retaining 95 % of the original graph). We evaluate different graph size configurations, ranging from 95 % to 70 % node retention, to determine the least impactful node set performance. Our experiments on three real-world datasets reveal that reducing nodes can decrease computation time by up to 29%, and as a byproduct of removing noise, even improve the prediction accuracy.

关键词： Training Accuracy Graph convolutional networks Roads Noise Layout Evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Optimizing Wireless Sensor Network Topology with Deep Reinforcement Learning for Multi-Source/Destination Scenarios

Optimizing Wireless Sensor Network Topology with Deep Reinfo...

引用

IEEE/ACM International Symposium on Big Data Computing (BDC)

ISBN: (数字)9798350367300

ISBN: (纸本)9798350367317

Wireless sensor networks are widely valued for their effectiveness in real-time data collection. As the amount of data exchanged within such networks grows, designing a robust network topology that maximizes area coverage with minimal sensors has become a critical challenge. The choice of topology impacts key network metrics, including sensor coverage, communication range, connectivity, inference, and installation and management costsIn this paper, we address the Wireless Sensor Network Planning Problem with Multiple Sources/Destinations, presenting an optimization approach based on deep reinforcement learning. This problem is noteworthy, as sensors in various applications are often required to share data within distinct destinationsWe leverage deep reinforcement learning to effectively address the complex task of selecting optimal sensor locations. Our reinforcement learning agent dynamically learns network structure by iteratively adding and removing sensors, optimizing both sensor coverage and the total number of sensors used. Experiment across diverse scenarios demonstrate the effectiveness of our method for network planning problems of varying scales, achieving full coverage with fewer sensors than traditional approaches. Additionally, our approach also produce solutions for large instances where Mixed Integer programming solvers were not able to. Overall, our method was able to reduce the number of sensors used by up to 22.3% compared to other methods.

关键词： Measurement Integer programming Wireless sensor networks Network topology Deep reinforcement learning Real-time systems Sensors Planning Topology Optimization

来源：评论

学校读者我要写书评

暂无评论

TagVibra: push the limit of RFID-based vibration sensing 9

TagVibra: push the limit of RFID-based vibration sensing

引用

9th International Conference on Big Data Computing and Communications, BigCom 2023

作者： Li, Jian Li, Ping Zhu, Biaokai Dong, Chong Gong, Chao Lv, Zhao Anhui University Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei230601 China Anhui University of Technology Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Ma'anshan243032 China Shanxi Police College Taiyuan030401 China

ISBN: (纸本)9798350331240

RFID-based mechanical vibration detection is considered a promising method for many Internet of Things (IoT) applications. However, existing methods are affected by ambient interference and leakage from the reader signature, which makes it difficult to obtain high-precision detection results. To overcome this limitation, this paper introduces TagVibra, a high-precision non-contact vibration sensing system based on RFID technology. By leveraging the nonlinear effect inside the tag and the modulation mechanism of RFID, TagVibra can achieve sub-millimeter level vibration detection accuracy. We implement TagVibra on our Universal Software Radio Peripheral (USRP) platform and evaluate its performance via experiments. The experimental results show that TagVibra can detect vibration with amplitude as low as 0.3mm, and the average estimation error below 0.7Hz when the vibration frequency is 100Hz. © 2023 IEEE.

关键词： Frequency estimation

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：