检索结果-内蒙古大学图书馆

System Architecture for Reading and Interpreting Physical Printouts of Medical Forms

学校读者我要写书评

暂无评论

System Architecture for Reading and Interpreting Physical Pr...

Annual Siberian Russian Workshop on Electron Devices and Materials (EDM)

作者： Ekaterina Snegireva Grigory R. Khazankin Igor Mikheenko Stream Data Analytics and Machine Learning laboratory Novosibirsk State University Novosibirsk Russia Novosibirsk State University Novosibirsk Russia Meshalkin National Medical Research Center Novosibirsk Russia

This article describes the developed architecture of the system module for processing and interpreting analog medical data. Patients often undergo examinations in various medical institutions, and since their results are often handed out to the patient in printed form, the receiving institution transfers them to its database manually. There is also a tendency to completely refuse analog media and use only digital ones. But in this case, another problem appears - either loss or conversion of the accumulated analog base into digital format. These days, automatic document management systems for medical institutions - Health information systems (HIS) - are actively developing. The software module developed in accordance with the architecture described in the article can be used by developers of various HIS to automate the work with analog data. If it is necessary, it can also be freely expanded by adding new modules for working with various analog data. In this article, we take ECG scans and medical test results as examples of such data. As a result of the work undertaken the prototype of the designed system was developed and tested.

关键词： Waste materials databases Prototypes Systems architecture Computer architecture Electrocardiography Medical tests

HERALD: A NATURAL LANGUAGE ANNOTATED LEAN 4 dataSET

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gao, Guoxiong Wang, Yutong Jiang, Jiedong Gao, Qi Qin, Zihan Xu, Tianyi Dong, Bin Peking University China National University of Singapore Singapore Center for Data Science Peking University China Beijing International Center for Mathematical Research The New Cornerstone Science Laboratory Peking University China Center for Machine Learning Research Peking University China

Verifiable formal languages like Lean have profoundly impacted mathematical reasoning, particularly through the use of large language models (LLMs) for automated reasoning. A significant challenge in training LLMs for these formal languages is the lack of parallel datasets that align natural language with formal language proofs. To address this challenge, this paper introduces a novel framework for translating the Mathlib4 corpus (a unified library of mathematics in formal language Lean 4) into natural language. Building upon this, we employ a dual augmentation strategy that combines tactic-based and informal-based approaches, leveraging the Lean-jixia system, a Lean 4 analyzer. We present the results of this pipeline on Mathlib4 as Herald (Hierarchy and Retrieval-based Translated Lean dataset). We also propose the Herald Translator, which is fine-tuned on Herald. Herald translator achieves a 93.2% accuracy (Pass@128) on formalizing statements in the miniF2F-test and a 22.5% accuracy on our internal graduate-level textbook dataset, outperforming InternLM2-Math-Plus-7B (74.0% and 7.5%) and TheoremLlama (50.1% and 4.0%). Furthermore, we propose a section-level translation framework for real-world applications. As a direct application of Herald translator, we have successfully translated a template section in the Stack project, marking a notable progress in the automatic formalization of graduate-level mathematical literature. Our model, along with the datasets, are open-sourced to the public.1 © 2024, CC BY.

关键词： Lean production

Gradient descent finds global minima of deep neural networks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Du, Simon S. Lee, Jason D. Li, Haochuan Wang, Liwei Zhai, Xiyu Machine Learning Department Carnegie Mellon University Data Science and Operations Department University of Southern California School of Physics Peking University Center for Data Science Peking University Beijing Institute of Big Data Research Key Laboratory of Machine Perception Moe School of Eecs Peking University Department of Eecs Massachusetts Institute of Technology

Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep over-parameterized neural network with residual connections (ResNet). Our analysis relies on the particular structure of the Gram matrix induced by the neural network architecture. This structure allows us to show the Gram matrix is stable throughout the training process and this stability implies the global optimality of the gradient descent algorithm. We further extend our analysis to deep residual convolutional neural networks and obtain a similar convergence result. Copyright © 2018, The Authors. All rights reserved.

关键词： Gradient methods

HmBERT: Historical Multilingual Language Models for Named Entity Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Schweter, Stefan März, Luisa Schmid, Katharina Çano, Erion Bayerische Staatsbibliothek München Digital Library/ Munich Digitization Center Munich Germany Digital Philology Research Group Data Mining and Machine Learning University of Vienna Austria Natural Language Processing Expert Center Data:Lab Volkswagen AG Munich Germany

Compared to standard Named Entity Recognition (NER), identifying persons, locations, and organizations in historical texts constitutes a big challenge. To obtain machine-readable corpora, the historical text is usually scanned and Optical Character Recognition (OCR) needs to be performed. As a result, the historical corpora contain errors. Also, entities like location or organization can change over time, which poses another challenge. Overall, historical texts come with several peculiarities that differ greatly from modern texts and large labeled corpora for training a neural tagger are hardly available for this domain. In this work, we tackle NER for historical German, English, French, Swedish, and Finnish by training large historical language models. We circumvent the need for large amounts of labeled data by using unlabeled data for pretraining a language model. We propose hmBert, a historical multilingual BERT-based language model, and release the model in several versions of different sizes. Furthermore, we evaluate the capability of hmBert by solving downstream NER as part of this year's HIPE-2022 shared task and provide detailed analysis and insights. For the Multilingual Classical Commentary coarse-grained NER challenge, our tagger HISTeria outperforms the other teams' models for two out of three languages. Copyright © 2022, The Authors. All rights reserved.

关键词： Optical character recognition

RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement

学校读者我要写书评

暂无评论

RecycleNet: Latent Feature Recycling Leads to Iterative Deci...

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Gregor Koehler Tassilo Wald Constantin Ulrich David Zimmerer Paul F. Jaeger Jörg K. H. Franke Simon Kohl Fabian Isensee Klaus H. Maier-Hein Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Information and Data Science School for Health Karlsruhe/Heidelberg Germany Helmholtz Imaging DKFZ National Center for Tumor Diseases (NCT) NCT Heidelberg a Partnership Between DKFZ University Medical Center Heidelberg Interactive Machine Learning Group DKFZ Machine Learning Lab University of Freiburg Freiburg Germany Latent Labs (***) London UK Applied Computer Vision Lab DKFZ Pattern Analysis and Learning Group Heidelberg University Hospital Heidelberg Germany

Despite the remarkable success of deep learning systems over the last decade, a key difference still remains between neural network and human decision-making: As humans, we can not only form a decision on the spot, but also ponder, revisiting an initial guess from different angles, distilling relevant information, arriving at a better decision. Here, we propose RecycleNet, a latent feature recycling method, instilling the pondering capability for neural networks to refine initial decisions over a number of recycling steps, where outputs are fed back into earlier network layers in an iterative fashion. This approach makes minimal assumptions about the neural network architecture and thus can be implemented in a wide variety of contexts. Using medical image segmentation as the evaluation environment, we show that latent feature recycling enables the network to iteratively refine initial predictions even beyond the iterations seen during training, converging towards an improved decision. We evaluate this across a variety of segmentation benchmarks and show consistent improvements even compared with top-performing segmentation methods. This allows trading increased computation time for improved performance, which can be beneficial, especially for safety-critical applications.

关键词：

On the Effectiveness of Heterogeneous Ensemble Methods for Re-Identification

学校读者我要写书评

暂无评论

On the Effectiveness of Heterogeneous Ensemble Methods for R...

International Conference on machine learning and Applications (ICMLA)

作者： Simon Klüttermann Jérôme Rutinowski Frederik Polachowski Anh Nguyen Britta Grimme Moritz Roidl Emmanuel Müller TU Dortmund University Dortmund Germany Lamarr Institute for Machine Learning and Artificial Intelligence Dortmund Germany Paderborn University Paderborn Germany Research Center Trustworthy Data Science and Security Dortmund Germany

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

In this contribution, we introduce a novel ensemble method for the re-identification of industrial entities, using images of chipwood pallets and galvanized metal plates as dataset examples. Our algorithms replace commonly used, complex siamese neural networks with an ensemble of simplified, rudimentary models, providing wider applicability, especially in hardware-restricted scenarios. Each ensemble sub-model uses different types of extracted features of the given data as its input, allowing for the creation of effective ensembles in a fraction of the training duration needed for more complex state-of-the-art models. We reach state-of-the-art performance at our task, with a Rank-1 accuracy of over 77% and a Rank-10 accuracy of over 99%, and introduce five distinct feature extraction approaches, and study their combination using different ensemble methods.

关键词： Training Accuracy Neural networks Metals Feature extraction Silicon Ensemble learning Security Reliability Pallets

The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Lei Su, Weijie J. School of Mathematical Sciences Peking University Beijing China Center for Machine Learning Research Peking University Beijing China Wharton Statistics and Data Science Department University of Pennsylvania Philadelphia United States

In this paper, we study the implicit regularization of stochastic gradient descent (SGD) through the lens of dynamical stability (Wu et al., 2018). We start by revising existing stability analyses of SGD, showing how the Frobenius norm and trace of Hessian relate to different notions of stability. Notably, if a global minimum is linearly stable for SGD, then the trace of Hessian must be less than or equal to 2/η, where η denotes the learning rate. By contrast, for gradient descent (GD), the stability imposes a similar constraint but only on the largest eigenvalue of Hessian. We then turn to analyze the generalization properties of these stable minima, focusing specifically on two-layer ReLU networks and diagonal linear networks. Notably, we establish the equivalence between these metrics of sharpness and certain parameter norms for the two models, which allows us to show that the stable minima of SGD provably generalize well. By contrast, the stability-induced regularization of GD is provably too weak to ensure satisfactory generalization. This discrepancy provides an explanation of why SGD often generalizes better than GD. Note that the learning rate (LR) plays a pivotal role in the strength of stability-induced regularization. As the LR increases, the regularization effect becomes more pronounced, elucidating why SGD with a larger LR consistently demonstrates superior generalization capabilities. Additionally, numerical experiments are provided to support our theoretical findings. © 2023, CC BY-SA.

关键词： Stability

Advances in Self-Organizing Maps, learning Vector Quantization, Clustering and data Visualization 1

学校读者我要写书评

暂无评论

丛书名： Advances in Intelligent Systems and Computing

1000年

作者： Alfredo Vellido Karina Gibert Cecilio Angulo José David Martín Guerrero

People flow prediction technology for crowd navigation

学校读者我要写书评

暂无评论

NTT Technical Review 2018年第8期16卷 47-52页

作者： Sato, Daisuke Shiohara, Hisako Miyamoto, Masaru Ueda, Naonori Proactive Navigation Project NTT Service Evolution Laboratories Japan Service Innovation Laboratory NTT Service Evolution Laboratories Japan Ueda Research Laboratory Japan Machine Learning and Data Science Center NTT Communication Science Laboratories Japan

We are investigating the use of incomplete observation data in order to predict the large-scale flow of people for major events such as the Olympic Games and to derive guidance measures in advance to prevent the occurrence of congestion. In this article, we introduce a spatio-temporal variable online prediction algorithm for forecasting congestion risk, and we explain our research and development efforts to utilize the algorithm. © 2018 Nippon Telegraph and Telephone Corp. All rights reserved.

关键词： Risk assessment