检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Bengs, Viktor Hüllermeier, Eyke Waegeman, Willem Munich Center for Machine Learning Germany Department of Data Analysis and Mathematical Modeling Ghent University Belgium

It is well known that accurate probabilistic predictors can be trained through empirical risk minimisation with proper scoring rules as loss functions. While such learners capture so-called aleatoric uncertainty of predictions, various machine learning methods have recently been developed with the goal to let the learner also represent its epistemic uncertainty, i.e., the uncertainty caused by a lack of knowledge and data. An emerging branch of the literature proposes the use of a second-order learner that provides predictions in terms of distributions on probability distributions. However, recent work has revealed serious theoretical shortcomings for second-order predictors based on loss minimisation. In this paper, we generalise these findings and prove a more fundamental result: There seems to be no loss function that provides an incentive for a second-order learner to faithfully represent its epistemic uncertainty in the same manner as proper scoring rules do for standard (first-order) learners. As a main mathematical tool to prove this result, we introduce the generalised notion of second-order scoring *** Codes 68T37 (Primary) 68T30 (Secondary) Copyright © 2023, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Determining the Genre of Music from a Melody Using machine learning and Parallel data Processing

Determining the Genre of Music from a Melody Using Machine L...

引用

Information Computing and Processing (ICP), Seminar on

作者： Danila A. Solodennikov Krystina A. Makoveichuk Department of Data Analysis and Machine Learning Financial University under the Government of the Russian Federation Moscow Russia

This article describes the author’s methodology for determining the genre of music from a melody using machine learning and parallel data processing. For determination is used dataset formed by the author, on the basis of which the model is trained and the genre is predicted on the test data. Yandex technologies, parallel programming, and Python data processing models are used in the work. There are also examples of training and test samples, model operation, data cleaning and dataset analysis methods. The work built neural network to identify genres and output results. The results vary from 35% to 50% and it should be noted that the dataset is rather small, so with bigger dataset we can await much higher result.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PITFALLS OF EPISTEMIC UNCERTAINTY QUANTIFICATION THROUGH LOSS MINIMISATION

arXiv

引用

arXiv 2022年

作者： Bengs, Viktor Hüllermeier, Eyke Waegeman, Willem Germany Munich Center for Machine Learning Germany Department of Data Analysis and Mathematical Modeling Ghent University Belgium

Uncertainty quantification has received increasing attention in machine learning in the recent past. In particular, a distinction between aleatoric and epistemic uncertainty has been found useful in this regard. The latter refers to the learner's (lack of) knowledge and appears to be especially difficult to measure and quantify. In this paper, we analyse a recent proposal based on the idea of a second-order learner, which yields predictions in the form of distributions over probability distributions. While standard (first-order) learners can be trained to predict accurate probabilities, namely by minimising suitable loss functions on sample data, we show that loss minimisation does not work for second-order predictors: The loss functions proposed for inducing such predictors do not incentivise the learner to represent its epistemic uncertainty in a faithful *** Codes 68T37 (Primary) 68T30 (Secondary) Copyright © 2022, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

machine learning Technologies for Bakery Management Decisions 24

Machine Learning Technologies for Bakery Management Decision...

引用

24th International Conference on Digital Signal Processing and its Applications, DSPA 2022

作者： Andriyanov, Nikita Dementiev, Vitaly Tashlinsky, Alexandr Danilov, Andrey Financial University under the Government of the Russian Federation Department of the Data Analysis and Machine Learning Moscow Russia Ulyanovsk State Technical University Department of the Telecommunications Ulyanovsk Russia Ulyanovsk State Technical University Department of the Radio Engineering Ulyanovsk Russia Llc Hlebnitsca Department of the Management Izhevsk Russia

ISBN: (纸本)9781665494434

The paper discusses using Deep Stream technologies in tasks for predicting best locations for deployment the bakeries. Such methods provides the calculation of people going through possible bakery and use convolutional neural networks for detection people and some effective algorithms for counting. The proposed solution allows deploying successful bakeries and keeping money in real production. Furthermore a lot of applied data science models were used for data analysis in these conditions. The paper discusses in detail the regression, factorial, cluster and discriminant analysis on the example of real data on the operation of a chain of bakeries with changes to preserve trade secrets. The analysis made it possible to simplify the decision-making process for managers among many factors. Moreover, the proposed method made it possible to predict profitability when opening a new point and explore various models of its development. Comparison results are provided for 3 models. The choice was made in favor of one of them. This choice resulted in the opening of a profitable bakery with a high profit margin for the retail market. The regression, factor and cluster analysis results show good opportunities to apply the results of the analysis for making management decisions when choosing the location of bakeries. © 2022 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Developing a Strategy for the Digital Transformation of an Educational Organization Based on Cloud Technology

Developing a Strategy for the Digital Transformation of an E...

引用

2023 Seminar on Information Systems Theory and Practice, ISTP 2023

作者： Olifirov, Alexander V. Makoveichuk, Krystina A. Petrenko, Sergei A. Department of Economics and Finance V.I. Vernadsky Crimean Federal University Yalta Russia Department of Data Analysis Machine Learning Financial University under the Government of the Russian Federation Moscow Russia Department of Information Security Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia

ISBN: (纸本)9798350345193

The article examines the theory and practical implementation of a digital transformation strategy. It was found that the main stages of formation of the digital transformation strategy of the organization are determined by: the use of digital services, individualization of a particular instance of the service, the involvement of the end consumer in the process, customer support throughout the life cycle of the service. Six main stages of implementation of the strategy of digital transformation of the educational process based on the use of cloud technology were formed. Opportunities and threats to the use of cloud technology in the educational space were identified. The experience of using the cloud service "1C: Fresh" in the formation of more than one hundred information bases in the training of specialists in the field of economics and finance was obtained. It was shown that the use of cloud technologies with the provision of students with access to the cloud service of 1C in the educational space of the university simulates the production activities of future specialists in real time. In this case, up-to-date and daily updated for the current legislation programs are used, functionality, cybersecurity and a high degree of data security are maintained at the proper level. ©2023 IEEE.

关键词： Information services

来源：评论

学校读者我要写书评

暂无评论

Training Artificial Neural Network to Classify Correct and Erroneous Interpretations of Visual Stimuli before Behavioral Response 6

Training Artificial Neural Network to Classify Correct and E...

引用

6th Scientific School "Dynamics of Complex Networks and their Applications", DCNA 2022

作者： Kuc, Alexander Batmanova, Alisa Maksimenko, Vladimir Immanuel Kant Baltic Federal University Baltic Center for Artificial Intelligence and Neurotechnology Kaliningrad Russia Financial University The Government of the Russian Federation Department of Data Analysis and Machine Learning Moscow Russia Innopolis University Neuroscience and Cognitive Technology Lab Republic of Tatarstan Russia

ISBN: (数字)9781665461740

ISBN: (纸本)9781665461740

We have trained an artificial neural network (ANN) to predict correct and erroneous interpretations of complex visual stimuli, Necker cubes with different levels of ambiguity. For the selected configuration of ANN, the classification accuracy was 88%. These results are prospective for developing the new-generation assistive technologies. © 2022 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Ensemble forecasting method 23

Ensemble forecasting method

引用

23rd International Conference on Soft Computing and Measurement, SCM 2020

作者： Ivanyuk, V.A. Tsvirkun, A.D. Department of Data Analysis and Machine Learning Financial University under the Government of the Russian Federation 49 Leningradsky Prospekt Moscow125993 Russia Department of Higher Mathematics Bauman Moscow State Technical University Moscow Russia V.A. Trapeznikov Institute of Control Sciences of RAS Moscow Russia

The purpose of this article is to analyze the time series based on aggregate forecasting methods. Forecasting time series comprises an important scientific and technical task which is relevant in various sectors of economy and production. The main objective of any forecasting process is to get the ability to assess trends in changes to a particular factor. To predict the behaviour of future processes, a qualitative analysis of data is required, which provides the basis for the forecast. It is also important to choose the appropriate forecasting method. The forecast obtained may not be always correct, so it is crucial to determine how accurately it is built. In the present paper, characteristics of time series are provided. The main mathematical methods of time series forecasting are analyzed and their classification is presented. Criteria for the accuracy and reliability of forecasting models are defined. The accuracy of the forecast is an important criterion for evaluating the forecasting method. The aggregate ensemble forecast has proven to be an effective method for enhancing the accuracy of forecasting. The article provides an example of constructing an aggregate ensemble forecast. The types of nonlinear models are described and several methods are selected for constructing the aggregate ensemble forecast. The practical application of exponential smoothing is considered, the MA (moving average) model and the AR (autoregressive) model are constructed. © 2020 Institute of Physics Publishing. All rights reserved.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Neural networks and their application in forecasting problems 23

Neural networks and their application in forecasting problem...

引用

23rd International Conference on Soft Computing and Measurement, SCM 2020

作者： Ivanyuk, V.A. Pashchenko, F.F. Department of Data Analysis and Machine Learning Financial University under the Government of the Russian Federation 49 Leningradsky Prospekt Moscow125993 Russia Department of Higher Mathematics Bauman Moscow State Technical University Moscow Russia V.A. Trapeznikov Institute of Control Sciences of RAS Moscow Russia

The report describes popular machine learning methods and applications of neural networks. It reveals methods of training neural networks and offers a method of forecasting based on neural networks for modelling financial time series. Neural networks have recently gained in popularity among scholars. In particular, neural networks are widely used in the field of visualization and image recognition. But the practical significance of neural networks does not end there, they also find usage in such areas as forecasting, classification, clustering and modelling. This success can mainly be attributed to the remarkable property of models based on neural networks – they can «see» non-linear connections in contrast to many models, which for the most part have linear connections only. Currently, the use of neural networks is developing in the following directions: Stock market and macroeconomic forecasting (Neuro XL, OptimuStock, StocksNeural);Speech recognition and man-machine dialogue (Siri, Alexa, Cortana, Alice);Imitation of intellectual activity (weak AI in Siri, Alexa, Cortana, Alice);Improving low-quality and noisy information (DeepImagePrior). The advantages of using neural networks include: versatility. simplicity. Neural networks are able to model dependencies also in cases when there is a large number of variables. © 2020 Institute of Physics Publishing. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Forecasting the dynamics of financial time series based on neural networks 23

Forecasting the dynamics of financial time series based on n...

引用

23rd International Conference on Soft Computing and Measurement, SCM 2020

作者： Ivanyuk, V.A. Abdikeev, N.M. Tsvirkun, A.D. Department of Data Analysis and Machine Learning Financial University under the Government of the Russian Federation 49 Leningradsky Prospekt Moscow125993 Russia Department of Higher Mathematics Bauman Moscow State Technical University Moscow Russia V.A. Trapeznikov Institute of Control Sciences of RAS Moscow Russia

Forecasting is one of the high-demand data mining problems, but also a very difficult one. The difficulties of forecasting are associated with insufficient quality and quantity of input data, the changes in the environment where the process takes place, and the impact of subjective factors. A forecast always implies some margin of error, which depends on the forecast model used and the completeness of the input data. Methods based on neural networks are the most relevant and highly-demanded techniques today. Neural networks are great for finding accurate solutions in an environment characterized by complex or fragmented information. In the field of finance and economics, the values of time series parameters can be more accurately modelled using neural analysis methods. Artificial neural networks have more common and flexible functional forms than statistical methods. They can generalize information and provide a qualitative forecast under conditions of uncertainty and crisis. The article proposes a forecasting model based on a neural network that can predict the price of a financial asset in a well-defined time interval. Ten technical indicators are used as input signals, and the closing price of the next period is used as an output signal. © 2020 Institute of Physics Publishing. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Using Generative Models to Improve Fire Detection Efficiency

Using Generative Models to Improve Fire Detection Efficiency

引用

Information Technology and Nanotechnology (ITNT), International Conference on

作者： Nikita Andriyanov Alexandr Kim Xenin Fao Data Analysis and Machine Learning Department Financial University under the Government of the Russian Federation Moscow Russia Data Science Department Huazhong University of Science and Technology Huazhong China

ISBN: (数字)9798350372939

ISBN: (纸本)9798350372946

The paper discusses generative artificial intelligence technologies used to improve the efficiency of fire detection in satellite images. Different detector architectures are proposed and compared in terms of accuracy. It is found that the use of generative models to expand the training sample is on average 1–2% more effective than the use of standard augmentations. The combined method of expanding the training image base can improve the accuracy by 4-5%. In addition, the right approach in generative prompts can also improve the accuracy metrics of the models.

关键词： Training Measurement YOLO Accuracy Image databases Detectors Satellite images

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：