检索结果-内蒙古大学图书馆

Artificial neural network-based method to classify sedimentary rocks 12

学校读者我要写书评

暂无评论

Artificial neural network-based method to classify sedimenta...

12th International Conference on Sensing Technology, ICST 2018

作者： Figueiredo, Rodrigo Marques Veronez, Mauricio Roberto Wohnrath, Francisco Manoel Da Silva, Marcio Rosa Gonzaga, Luiz Kupssinsku, Lucas Silveira Bordin, Fabiane Brum, Diego Cazarin, Caroline Lessio Graduate Program in Geology Unisinos University Saõ Leopoldo Brazil Advanced Visualization and Geoinformatics Laboratory Unisinos University Saõ Leopoldo Brazil Graduate Program in Electrical Engineering Unisinos University Saõ Leopoldo Brazil Graduate Program in Applied Computing Unisinos University Saõ Leopoldo Brazil Rio de Janeiro Brazil

ISBN: (纸本)9781538651476

In a geological study, an important step is to determine the type of sedimentary rock or its grain size. Such a determination requires accurate analysis in the field or in a laboratory. As the size of the study area grows, this activity can be time consuming and error prone because the number of specialists working under rigid criteria also increases. This paper proposes a novel methodology to classify grain size using unique wavelength reflectance data and artificial neural networks. The results indicate that the proposed method can be reliably used in the field. © 2018 IEEE.

关键词： Neural networks

On Training Flexible Robots using Deep Reinforcement Learning

学校读者我要写书评

暂无评论

On Training Flexible Robots using Deep Reinforcement Learnin...

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Zach Dwiel Madhavun Candadai Mariano Phielipp Intel AI Labs Bloomington IN U.S.A Program in Cognitive Science and School of Informatics Computing and Engineering at Indiana University Bloomington IN U.S.A Intel AI Labs Phoenix AZ U.S.A

The use of robotics in controlled environments has flourished over the last several decades and training robots to perform tasks using control strategies developed from dynamical models of their hardware have proven very effective. However, in many real-world settings, the uncertainties of the environment, the safety requirements and generalized capabilities that are expected of robots make rigid industrial robots unsuitable. This created great research interest in developing control strategies for flexible robot hardware for which building dynamical models are challenging. In this paper, inspired by the success of deep reinforcement learning (DRL), we systematically study the efficacy of policy search methods using DRL in training flexible robots. Our results indicate that DRL is successfully able to learn efficient and robust policies for complex tasks at various degrees of flexibility. We also note that DRL using Deep Deterministic Policy Gradients can be sensitive to the choice of sensors and adding more informative sensors does not necessarily make the task easier to learn.

关键词：

Plan-based intention revision 32

学校读者我要写书评

暂无评论

Plan-based intention revision

32nd AAAI Conference on Artificial Intelligence, AAAI 2018

作者： Amos-Binks, Adam Michael Young, R. Department of Computer Science NC State University RaleighNC27695 United States School of Computing The Entertainment Arts and Engineering Program University of Utah Salt Lake CityUT84112 United States

ISBN: (纸本)9781577358008

To extend the behavior range of character agents in story plans, we have defined plan-based intention revision with two key properties. The first is when an agent should reconsider an intention frame. We use a causal-link threat to operationalize the reconsider function from the BDI control loop. The second property describes how an agent should revise their intentions. Based on when a P-GOAL should be dropped, we allow an intention revision when no subplan exists for a reconsidered intention. Finally, we discuss evaluating these two properties using the QUEST cognitive model. Copyright © 2018, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

High-Performance Metal-Ferroeletric-Semiconductor Nanosheet Line Tunneling Field Effect Transistors with Strained SiGe

学校读者我要写书评

暂无评论

High-Performance Metal-Ferroeletric-Semiconductor Nanosheet ...

International Conference on Simulation of Semiconductor Processes and Devices (SISPAD)

作者： Narasimhulu Thoti Yiming Li Sekhar Reddy Kola Seiji Samukawa Parallel and Scientific Computing Laboratory 1001 Ta-Hsueh Rd. Hsinchu Taiwan EECS International Graduate Program 1001 Ta-Hsueh Rd. Hsinchu Taiwan Institute of Communications Engineering 1001 Ta-Hsueh Rd. Hsinchu Taiwan National Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu Taiwan Institute of Fluid Science Tohoku University 1001 Ta-Hsueh Rd. Sendai Japan

ISBN: (数字)9784863487635

ISBN: (纸本)9781728173542

Nanosheet line tunnel-field effect transistors (NLTFETs) are for the first time proposed by utilizing the advantages of ferroelectricity through HZO materials. Three ferroelectric line TFETs have been proposed and investigated. Among these, the metal-ferroelectric-semiconductor (MFS) structure has shown superior performance than the other two variants. The factors of electric field and electron barrier tunneling have been addressed to govern the performance of these structures. In addition, the effects of the ferroelectric (Hf 0.5 Zr 0.5 O 2 ) thickness (t FE ) and the dielectric constant have been discussed. The MFS NLTFETs can effectively utilize the advantages of ferroelectric than the other variants. High on-current of 175.6 μA/μm and low off-current of 38.4 aA/μm are achieved at t FE of 4 nm through proper utilization of gate-overlap on to the drain side. Furthermore, the proposed MFS structure successfully delivers low average and minimum subthreshold swings even at very thin t FE .

关键词： Performance evaluation TFETs Tunneling Nanoscale devices Semiconductor process modeling Electric fields Silicon germanium

An application of neural networks to channel estimation of the ISDB-TB FBMC system

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Almeida, Jefferson Jesus Hengles Lopes, P.B. Akamine, Cristiano Omar, Nizam Postgraduate Program in Electrical Engineering and Computing Mackenzie Presbyterian University Sao Paulo Brazil

Due to the evolution of technology and the diffusion of digital television, many researchers are studying more efficient transmission and reception methods. This fact occurs because of the demand of transmitting videos with better quality using new standards such 8K SUPER Hi-VISION. In this scenario, modulation techniques such as Filter Bank Multi Carrier, associated with advanced coding and synchronization methods, are being applied, aiming to achieve the desired data rate to support ultra-high definition videos. Simultaneously, it is also important to investigate ways of channel estimation that enable a better reception of the transmitted signal. This task is not always trivial, depending on the characteristics of the channel. Thus, the use of artificial intelligence can contribute to estimate the channel frequency response, from the transmitted pilots. A classical algorithm called Back-propagation Training can be applied to find the channel equalizer coefficients, making possible the correct reception of TV signals. Therefore, this work presents a method of channel estimation that uses neural network techniques to obtain the channel response in the Brazilian Digital System Television, called ISDB-TB, using Filter Bank Multi Carrier. Copyright © 2018, The Authors. All rights reserved.

关键词： Channel estimation

Building resilience for long duration space flight: A multiple project study across multiple discipline areas with primary hosts as architecture and industrial design tertiary programs in USA and Australia 69

学校读者我要写书评

暂无评论

Building resilience for long duration space flight: A multip...

69th International Astronautical Congress: #InvolvingEveryone, IAC 2018

作者： Alexander, Sasha Bannova, Olga Kwon, EunSook Academic Program Industrial Design School of Computing Engineering and Mathematics Western Sydney University ParramattaNSW Australia Cullen School of Engineering Sasakawa International Center for Space Architecture University of Houston HoustonTX United States Industrial Design Program Gerald D Hines College of Architecture and Design University of Houston HoustonTX United States

International cooperation on space flight project development starts on earth by way of professional introductions between prospective host organizations and collaborators with major and minor actors. Complex prior projects provide insights and the ongoing foundational knowledge from which new innovations can launch and new ideas can come from both seasoned researchers, and commercial partnerships (NASA, SpaceX), but also fresh minds as the knowledge sets are brought together and interact to form new innovative perspectives. Universities as research test-beds for capturing the imaginations of new professional generations are an exciting environment to focus discipline skills and recalibrate career ambitions and trajectories. Space exploration exemplars as the International Space Station (ISS) provides an example of an enabling platform where cooperative relations in developing, constructing human habitation systems provide evidence that national and international collaborations are core to the development of future missions and lunar habitation. Future long-duration spaceflight and exploration missions will require from the crew to perform at their maximum capacity. Habitation architecture and spacecraft design must respect habitability needs including health, functional and safety requirements, which should be addressed at every stage of the design process: â€œconsidering people to be more than an 'element' of the system but its modifier and innovatorâ€¥ (Haeuplik-Meusburger S., Bannova O., 2016). This paper presents the results of a cross disciplinary approach to habitation system development for long-duration missions (LDMs) in relation to crew health systems;and alternate activities for managing stress triggers in confined environments and explored via a project-oriented strategy. Students from involved universities and programs have advanced their design for space interactions through identifying and acquiring information and knowledge, analysing it, and synthe

关键词： Product design

Are Traditional Deep Learning Model Approaches as Effective as a Retinal-Specific Foundation Model for Ocular and Systemic Disease Detection?

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yew, Samantha Min Er Lei, Xiaofeng Goh, Jocelyn Hui Lin Chen, Yibing Srinivasan, Sahana Chee, Miao-Li Pushpanathan, Krithi Zou, Ke Hou, Qingshan Da Soh, Zhi Xue, Cancan Yu, Marco Chak Yan Sabanayagam, Charumathi Tai, E. Shyong Sim, Xueling Wang, Yaxing Jonas, Jost B. Nangia, Vinay Yang, Gabriel Dawei Ran, Emma Anran Cheung, Carol Yim-Lui Feng, Yangqin Zhou, Jun Goh, Rick Siow Mong Zhou, Yukun Keane, Pearse A. Liu, Yong Cheng, Ching-Yu Tham, Yih-Chung Department of Ophthalmology Yong Loo Lin School of Medicine National University of Singapore Singapore Centre for Innovation and Precision Eye Health Yong Loo Lin School of Medicine National University of Singapore Singapore Singapore Singapore Singapore Eye Research Institute Singapore National Eye Centre Singapore Singapore Ophthalmology and Visual Science Academic Clinical Program Duke-NUS Medical School Singapore Singapore Saw Swee Hock School of Public Health National University of Singapore Singapore Singapore Duke-NUS Medical School Singapore Singapore Precision Health Research Singapore Singapore Beijing Tsinghua Changgung Hospital Tsinghua Medicine Tsinghua University Beijing China Tsinghua Medicine Tsinghua University Beijing China Rothschild Foundation Hospital Institut Français de Myopie Paris France New York Eye and Ear Infirmary of Mount Sinai Icahn School of Medicine at Mount Sinai New York United States Suraj Eye Institute Nagpur India Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong Hong Kong Centre for Medical Image Computing University College London London United Kingdom NIHR Biomedical Research Centre Moorfields Eye Hospital NHS Foundation Trust London United Kingdom Department of Medical Physics and Biomedical Engineering University College London London United Kingdom Institute of Ophthalmology University College London London United Kingdom

Background: RETFound, a self-supervised, retina-specific foundation model (FM), showed potential in downstream applications. However, its comparative performance with traditional deep learning (DL) models remains incompletely understood. This study aimed to evaluate RETFound against three ImageNet-pretrained supervised DL models (ResNet50, ViT-base, SwinV2) in detecting ocular and systemic diseases. Methods: We fine-tuned/trained RETFound and three DL models on full datasets, 50%, 20%, and fixed sample sizes (400, 200, 100 images, with half comprising disease cases;for each DR severity class, 100 and 50 cases were used. Fine-tuned models were tested internally using the SEED (53,090 images) and APTOS-2019 (3,672 images) datasets and externally validated on population-based (BES, CIEMS, SP2, UKBB) and open-source datasets (ODIR-5k, PAPILA, GAMMA, IDRiD, MESSIDOR-2). Model performance was compared using area under the receiver operating characteristic curve (AUC) and Z-tests with Bonferroni correction (P Copyright © 2025, The Authors. All rights reserved.

关键词： Ophthalmology

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina Aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential. © 2024, CC BY-NC-ND.

关键词： Large datasets

Hierarchical policy learning is sensitive to goal space design

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Dwiel, Zach Candadai, Madhavun Phielipp, Mariano Bansal, Arjun K. Intel AI Lab BloomingtonIN United States Program in Cognitive Science School of Informatics Computing and Engineering BloomingtonIN United States Intel AI Lab PhoenixAZ United States Intel AI Lab San DiegoCA United States

Hierarchy in reinforcement learning agents allows for control at multiple time scales yielding improved sample efficiency, the ability to deal with long time horizons and transferability of sub-policies to tasks outside the training distribution. It is often implemented as a master policy providing goals to a sub-policy. Ideally, we would like the goal-spaces to be learned, however, properties of optimal goal spaces still remain unknown and consequently there is no method yet to learn optimal goal spaces. Motivated by this, we systematically analyze how various modifications to the ground-truth goal-space affect learning in hierarchical models with the aim of identifying important properties of optimal goal spaces. Our results show that, while rotation of ground-truth goal spaces and noise had no effect, having additional unnecessary factors significantly impaired learning in hierarchical models. Copyright © 2019, The Authors. All rights reserved.

关键词： Hierarchical systems