检索结果-内蒙古大学图书馆

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Joseph Pemberton Ellen Boven Richard Apps Rui Ponte Costa Bristol Computational Neuroscience Unit Dept. of Computer Science SCEEM University of Bristol UK Bristol Computational Neuroscience Unit School of Phys. Pharm. and Neuroscience University of Bristol UK School of Phys. Pharm. and Neuroscience University of Bristol UK

ISBN: (纸本)9781713845393

The brain solves the credit assignment problem remarkably well. For credit to be assigned across neural networks they must, in principle, wait for specific neural computations to finish. How the brain deals with this inherent locking problem has remained unclear. Deep learning methods suffer from similar locking constraints both on the forward and feedback phase. Recently, decoupled neural interfaces (DNIs) were introduced as a solution to the forward and feedback locking problems in deep networks. Here we propose that a specialised brain region, the cerebellum, helps the cerebral cortex solve similar locking problems akin to DNIs. To demonstrate the potential of this framework we introduce a systems-level model in which a recurrent cortical network receives online temporal feedback predictions from a cerebellar module. We test this cortico-cerebellar recurrent neural network (ccRNN) model on a number of sensorimotor (line and digit drawing) and cognitive tasks (pattern recognition and caption generation) that have been shown to be cerebellar-dependent. In all tasks, we observe that ccRNNs facilitates learning while reducing ataxia-like behaviours, consistent with classical experimental observations. Moreover, our model also explains recent behavioural and neuronal observations while making several testable predictions across multiple levels. Overall, our work offers a novel perspective on the cerebellum as a brain-wide decoupling machine for efficient credit assignment and opens a new avenue between deep learning and neuroscience.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Vector Quantized Shape Code for Amodal Blastomere Instance Segmentation

Learning Vector Quantized Shape Code for Amodal Blastomere I...

引用

IEEE International Symposium on Biomedical Imaging

作者： Won-Dong Jang Donglai Wei Xingxuan Zhang Brian Leahy Helen Yang James Tompkin Dalit Ben-Yosef Daniel Needleman Hanspeter Pfister School of Engineering and Applied Sciences Harvard University MA USA Boston College MA USA Department of Molecular and Cellular Biology Harvard University MA USA Harvard Graduate Program in Biophysics Harvard University MA USA Department of Computer Science Brown University RI USA Tel Aviv Sourasky Medical Center Fertility & IVF Institute Israel Dept. of Cell and Developmental Biology Sagol School of Neuroscience Tel Aviv University Israel

Blastomere instance segmentation is important for analyzing embryos’ abnormality. To measure the accurate shapes and sizes of blastomeres, their amodal segmentation is necessary. Amodal instance segmentation aims to recover an object’s complete silhouette even when the object is not fully visible. For each detected object, previous methods directly regress the target mask from input features. However, images of an object under different amounts of occlusion should have the same amodal mask output, making it harder to train the regression model. To alleviate the problem, we propose to classify input features into intermediate shape codes and recover complete object shapes. First, we pre-train the Vector Quantized Variational Autoencoder (VQ-VAE) model to learn these discrete shape codes from ground truth amodal masks. Then, we incorporate the VQ-VAE model into the amodal instance segmentation pipeline with an additional refinement module. We also detect an occlusion map to integrate occlusion information with a backbone feature. As such, our network faithfully detects bounding boxes of amodal objects. On an internal embryo cell image benchmark, the proposed method outperforms previous state-of-the-art methods. To show generalizability, we show segmentation results on the public KINS natural image benchmark. Our method would enable accurate measurement of blastomeres in In Vitro Fertilization (IVF) clinics, potentially increasing the IVF success rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional quantitative phase imaging evaluating glioblastoma targeting CAR T-cell efficacy 11

Three-dimensional quantitative phase imaging evaluating glio...

引用

Quantitative Phase Imaging XI 2025

作者： Serafini, Caroline E. Davarzani, Amin Cappabianca, Dan Collazos, Daniela Baez Li, Zhenmin Mamaghani, Deniz Tommasi, Anna Sarko, Lauren La Vonne Denne, Nina Mao, Leidong Saha, Krishanu Karumbaiah, Lohitash Robles, Francisco E. George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology AtlantaGA United States Wallace H. Coulter Dept. of Biomedical Engineering Georgia Institute of Technology Emory University AtlantaGA United States School of Electrical and Computer Engineering College of Engineering University of Georgia AthensGA United States Regenerative Bioscience Center University of Georgia AthensGA United States Department of Biomedical Engineering University of Wisconsin-Madison MadisonWI United States Wisconsin Institute for Discovery University of Wisconsin-Madison MadisonWI United States School of Electrical and Computer Engineering Georgia Institute of Technology 266 Ferst Drive AtlantaGA United States Department of Cellular Biology University of Georgia AthensGA United States Division of Neuroscience Biomedical and Translational Sciences Institute University of Georgia AthensGA United States Edgar L. Rhodes Center for Animal and Dairy Science College of Agriculture and Environmental Science University of Georgia AthensGA United States

ISBN: (纸本)9781510684065

Glioblastoma (GBM) is a highly aggressive brain tumor with limited treatment options and poor patient outcomes. While patient-derived spheroids offer a platform for studying GBM treatment, existing imaging modalities are often destructive or limited to endpoint analyses. Here, we present quantitative Oblique Back- illumination Microscopy (qOBM) as a novel, label-free imaging technique for real-time, non-invasive monitoring of GBM spheroids treated with tumor targeting chimeric antigen receptor T-cells (CAR T-cells). qOBM overcomes existing imaging limitations by providing high-resolution, 3D quantitative phase imaging through epi-illumination, enabling longitudinal visualization of cellular and subcellular processes within thick spheroids. Here, we apply qOBM to monitor the responses of GBM spheroids derived from three unique patient cell lines to targeted CAR T-cell immunotherapy and non-targeted controls. With this, we capture changes in the spheroids over 72 hours of treatment, allowing for visualization of processes such as CAR T-cell infiltration, mitosis, and apoptosis. Further, using images from GBM/CAR T cell cocultures, we develop a machine learning model for predicting spheroid cytotoxicity rates. Our findings establish qOBM as a powerful, non-destructive tool for longitudinal GBM spheroid toxicity monitoring and demonstrate its potential to advance personalized cancer therapy by providing real-time insight into treatment efficacy. © 2025 SPIE.

关键词： T-cells

来源：评论

学校读者我要写书评

暂无评论

A Neural Network Based Modeling of Closed Room Thermal Comfort Environmental Prediction for Sensor Hub 17

A Neural Network Based Modeling of Closed Room Thermal Comfo...

引用

17th International Conference on Electrical Engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON 2020

作者： Thongkhome, Pornpawee Dejdumrong, Natasha Triamudomsuksa Pattanakarn School Science-Mathematics Program Bangkok Thailand King Mongkut's University of Technology Thonburi Dept. of Computer Engineering Bangkok Thailand

ISBN: (纸本)9781728164861

Currently, environmental protection and intelligence system are topics of interest in smart homes and intelligent buildings. This work represents an environmental prediction study of the closed room which installed a split-type air-conditioning system and a newly designed sensor hub using a feed-forward back-propagation artificial neural network-based prediction for human thermal comfort and indirectly concerned to the growth or existence of diseases, contagious diseases and allergies. The RPROP algorithm was utilized to train the closed room environmental parameters that get from sensor hub especial relative humidity in the ANN model and validate the model by using cohen's kappa and ROC curve to represents the degree of accuracy and reliability. The result obtained from the ANN trained data agreed closely with those obtained from a sensor hub with the high perfect agreement. The benefit of the ANN-based strategy in this study could be utilized for the design of a sensor hub that can realize the adaptive adjustment of environmental parameters through the air conditioning system. © 2020 IEEE.

关键词： Thermal comfort

来源：评论

学校读者我要写书评

暂无评论

The effect of phased recurrent units in the classification of multiple catalogs of astronomical lightcurves

arXiv

引用

arXiv 2021年

作者： Donoso-Oliva, Cristobal Cabrera-Vives, G. Protopapas, P. Carrasco-Davis, R. Estevez, P.A. Dept. of Computer Science Universidad De Concepcion Millennium Institute of Astrophysics Chile Institute for Applied Computational Science Harvard University Gatsby Computational Neuroscience Unit University College London Dept. of Electrical Engineering Universidad de Chile

来源：评论

学校读者我要写书评

暂无评论

Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time 21

Deep inference of latent dynamics with spatio-temporal super...

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Feng Zhu Andrew R. Sedler Harrison A. Grier Nauman Ahad Mark A. Davenport Matthew T. Kaufman Andrea Giovannucci Chethan Pandarinath Neuroscience Graduate Program Emory University Center for Machine Learning Georgia Tech Computational Neuroscience Graduate Program The University of Chicago School of Electrical and Computer Engineering Georgia Tech Dept. of Organismal Biology and Anatomy The University of Chicago and Neuroscience Institute The University of Chicago Joint Dept. of Biomedical Engineering UNC Chapel Hill and NC State University and UNC Chapel Hill Neuroscience Center and NC State/UNC Closed-Loop Engineering for Advanced Rehabilitation (CLEAR) Coulter Dept. of Biomedical Engineering Emory University and Georgia Tech and Dept. of Neurosurgery Emory University

ISBN: (纸本)9781713845393

Modern neural interfaces allow access to the activity of up to a million neurons within brain circuits. However, bandwidth limits often create a trade-off between greater spatial sampling (more channels or pixels) and the temporal frequency of sampling. Here we demonstrate that it is possible to obtain spatio-temporal super-resolution in neuronal time series by exploiting relationships among neurons, embedded in latent low-dimensional population dynamics. Our novel neural network training strategy, selective backpropagation through time (SBTT), enables learning of deep generative models of latent dynamics from data in which the set of observed variables changes at each time step. The resulting models are able to infer activity for missing samples by combining observations with learned latent dynamics. We test SBTT applied to sequential autoencoders and demonstrate more efficient and higher-fidelity characterization of neural population dynamics in electrophysiological and calcium imaging data. In electrophysiology, SBTT enables accurate inference of neuronal population dynamics with lower interface bandwidths, providing an avenue to significant power savings for implanted neuroelectronic interfaces. In applications to two-photon calcium imaging, SBTT accurately uncovers high-frequency temporal structure underlying neural population activity, substantially outperforming the current state-of-the-art. Finally, we demonstrate that performance could be further improved by using limited, high-bandwidth sampling to pretrain dynamics models, and then using SBTT to adapt these models for sparsely-sampled data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Constructing A Creative Service Software with Semantic Web 8

Constructing A Creative Service Software with Semantic Web

引用

8th International Conference on Dependable Systems and Their Applications, DSA 2021

作者： Huang, Pei-Shu Fahmi, Faisal Wang, Feng-Jian Yang, Hongji Dept. of Computer Science National Yang-Ming Chiao-Tung University Hsinchu City Taiwan EECS Int’l Graduate Program National Yang-Ming Chiao-Tung University Hsinchu City Taiwan Information and Library Science Airlangga University Surabaya City Indonesia Department of Informatics University of Leicester Leicester United Kingdom

ISBN: (纸本)9781665443913

In software development, Service Oriented Architecture (SOA) and creative computing can be adopted to utilize multiple-domain knowledges to construct service software possessing creative properties, i.e., novel, useful, and surprising. In the past, several theoretical evaluation metrics have been proposed to measure creativity of a software system. However, a systematic practical method to construct creative service software is rarely considered in current researches. In this paper, we propose a model for creative service software development based on semantic web, which is applied in two phases: domain-creative requirement specification and semantic-based service design. The model can reduce communication work between domain experts and software engineers, improve traceability of the specifications, and improve machine readability during the generation of creativity. After the model of service design is validated for completeness and consistency, the creative service software is well-designed and can be implemented and reused effectively without losing of creativity. © 2021 IEEE.

关键词： Semantic Web

来源：评论

学校读者我要写书评

暂无评论

Engineered Modular Neuronal Networks-on-Chip Represent Structure-Function Relationship

SSRN

引用

SSRN 2024年

作者： Habibey, Rouhollah Striebel, Johannes Latiftikhereshki, Roshanak Schmieder, Felix Nasiri, Rohollah Latifi, Shahrzad Universitäts-Augenklinik Bonn University of Bonn Dep. of Ophthalmology Ernst-Abbe-Straße 2 BonnD-53127 Germany CRTD - Center for Regenerative Therapies TU Dresden Dresden01307 Germany Dept. Neuroscience Italian Institute of Technology Genova Italy Department of Computer Engineering Faculty of Engineering Kermanshah Branch Azad University Kermanshah Iran Laboratory of Measurement and Sensor System Technique Faculty of Electrical and Computer Engineering TU Dresden Helmholtzstraße 18 Dresden01069 Germany Division of Nanobiotechnology Department of Protein Science Science for Life Laboratory KTH Royal Institute of Technology Solna Sweden AIMES Center for the Advancement of Integrated Medical and Engineering Sciences Department of Neuroscience Karolinska Institute Solna Sweden Department of Neurology David Geffen School of Medicine University of California Los Angeles Los AngelesCA United States Department of Neuroscience Rockefeller Neuroscience Institute West Virginia University MorgantownWV26506 United States

Brain function is substantially linked to the highly organized structure of neuronal networks. The structures of in vitro assembled neuronal circuits often vary between samples and change over time, making it challenging to reliably record network functional output and link it to network structure. Therefore, engineering neuronal structures with predefined geometry and reproducible functional features is essential to robustly model in vivo neuronal circuits. Here, we engineered thin microchannel devices to assemble 2D and 3D modular networks. The microchannel devices were coupled with a multi-electrode array (MEA) electrophysiology system to enable long-term electrophysiology recordings from microengineered circuits. Each network consisted of 64 modules connected to their adjacent modules by micron-sized channels. The microstructures physically confined neurons to the recording electrodes, which significantly improved the efficiency of electrophysiology readout. In addition, the microstructures maintained the modular network structure for weeks. Modular circuits within microfluidic devices showed consistent spatial patterns of activity over weeks, which was lacking in the randomly formed circuits. The number of physical connections per module was shown to influence the measured activity and functional connectivity parameters, which represents the impact of network structure on its functional output. We show that microengineered 3D modular networks with profound activity and higher number of functional connections recapitulate key functional features of developing cortex. Structurally and functionally stable 2D and 3D networks mimic the modular architecture of brain circuits and provide a robust and reproducible in vitro microphysiological system for basic and translational neuroscience research. © 2024, The Authors. All rights reserved.

关键词： Microfluidics

来源：评论

学校读者我要写书评

暂无评论

The Role of Big Data in Enhancing Student's Sustainable Development Awareness: A Case Study in Higher Education 2020

The Role of Big Data in Enhancing Student's Sustainable Deve...

引用

2nd International Conference on Big Data Engineering and Technology, BDET 2020

作者： Pane, Murty Magda Siregar, Christian Lake, Silverius C.J.M. Character Building Development Center Computer Science School of Computer Science Bina Nusantara University Jakarta Indonesia Character Building Development Center Mass Communication Program Communication Dept. Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9781450376839

This study objective is to find the general picture of the knowledge, attitude and behavior of students for sustainable development. It used the quantitative method with 160 students as the research subjects with the data collection technique of questionnaire distribution. The questionnaires are valid (the corrected item total correlations for knowledge, attitudes and behavior are: 0.745, 0.878 and 0.726) and reliable (α for knowledge, attitudes and behavior are: 0.985, 0.978 and 0.959). The positive nuances questionnaire's results are analyzed through a correlative analysis. The results showed scale 4 were chosen most for knowledge and attitude (41.40% and 42.93%), only in behavior the scale 3 was the most chosen (34.63%). The results concluded that the students tend to have positive knowledge, attitude and behavior towards the sustainable development, and the results will give strong support the sustainable future for human security. The results were connected with the big data, especially in social media and instant messaging where they can learn and get educated about sustainable development. © 2020 ACM.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Vyakarana: A colorless green benchmark for syntactic evaluation in indic languages

arXiv

引用

arXiv 2021年

作者： Patil, Rajaswa Dhillon, Jasleen Mahurkar, Siddhant Kulkarni, Saumitra Malhotra, Manav Baths, Veeky Cognitive Neuroscience Lab BITS Pilani Goa Campus Dept. of CS & IS BITS Pilani Goa Campus Data Science Institute Columbia University Dept. of Computer Engineering PICT Maharashtra India Dept. of Mathematics BITS Pilani Goa Campus

While there has been significant progress towards developing NLU resources for Indic languages, syntactic evaluation has been relatively less explored. Unlike English, Indic languages have rich morphosyntax, grammatical genders, free linear word-order, and highly inflectional morphology. In this paper, we introduce Vyakarana: a benchmark of Colorless Green sentences in Indic languages for syntactic evaluation of multilingual language models. The benchmark comprises four syntax-related tasks: PoS Tagging, Syntax Tree-dept. Prediction, Grammatical Case Marking, and Subject-Verb Agreement. We use the datasets from the evaluation tasks to probe five multilingual language models of varying architectures for syntax in Indic languages. Due to its prevalence, we also include a code-switching setting in our experiments. Our results show that the tokenlevel and sentence-level representations from the Indic language models (IndicBERT and MuRIL) do not capture the syntax in Indic languages as efficiently as the other highly multilingual language models. Further, our layerwise probing experiments reveal that while mBERT, DistilmBERT, and XLM-R localize the syntax in middle layers, the Indic language models do not show such syntactic localization. © 2021, CC BY.

关键词： Syntactics

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：