Pub Date : 2023-10-30DOI: 10.5604/01.3001.0053.9698
Robert Jarosz
This paper collects several applications of reinforcement learning in solving some problems related to game theory. The methods were selected to possibly show variety of problems and approaches. Selections includes Thompson Sampling, Q-learning, DQN and AlphaGo Zero using Monte Carlo Tree Search algorithm. Paper attempts to show intuition behind proposed algorithms with shallow explaining of technical details. This approach aims at presenting overview of the topic without assuming deep knowledge about statistics and artificial intelligence.
{"title":"Overview of selected reinforcement learning solutions to several game theory problems","authors":"Robert Jarosz","doi":"10.5604/01.3001.0053.9698","DOIUrl":"https://doi.org/10.5604/01.3001.0053.9698","url":null,"abstract":"This paper collects several applications of reinforcement learning in solving some problems related to game theory. The methods were selected to possibly show variety of problems and approaches. Selections includes Thompson Sampling, Q-learning, DQN and AlphaGo Zero using Monte Carlo Tree Search algorithm. Paper attempts to show intuition behind proposed algorithms with shallow explaining of technical details. This approach aims at presenting overview of the topic without assuming deep knowledge about statistics and artificial intelligence.","PeriodicalId":240434,"journal":{"name":"Computer Science and Mathematical Modelling","volume":"95 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139309767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.5604/01.3001.0053.9702
Robert Jarosz
This paper presents an overview of four selected solutions addressing problem of bidding in card game of contract bridge. In the beginning the basic rules are presented along with basic problem size estimation. Brief description of collected work is presented in chronological order, tracking evolution of approaches to the problem. While presenting solution a short description of mathematical base is attached. In the end a comparison of solution is made, followed by an attempt to estimate future development of techniques.
{"title":"Analysis of selected reinforcement learning applications in contract bridge","authors":"Robert Jarosz","doi":"10.5604/01.3001.0053.9702","DOIUrl":"https://doi.org/10.5604/01.3001.0053.9702","url":null,"abstract":"This paper presents an overview of four selected solutions addressing problem of bidding in card game of contract bridge. In the beginning the basic rules are presented along with basic problem size estimation. Brief description of collected work is presented in chronological order, tracking evolution of approaches to the problem. While presenting solution a short description of mathematical base is attached. In the end a comparison of solution is made, followed by an attempt to estimate future development of techniques.","PeriodicalId":240434,"journal":{"name":"Computer Science and Mathematical Modelling","volume":"35 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139309875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.5604/01.3001.0054.0092
Michał Zimoń, Rafał Kasprzyk
Object detection, a key application of machine learning in image processing, has achieved significant success thanks to advances in deep learning (Girshick et al. 2014). In this paper, we focus on analysing the vulnerability of one of the leading object detection models, YOLOv5x (Redmon et al. 2016), to adversarial attacks using specially designed interference known as “adversarial patches” (Brown et al. 2017). These disturbances, while often visible, have the ability to confuse the model, which can have serious consequences in real world applications. We present a methodology for generating these interferences using various techniques and algorithms, and we analyse their effectiveness in various conditions. In addition, we discuss potential defences against these types of attacks and emphasise the importance of security research in the context of the growing popularity of ML technology (Papernot et al. 2016). Our results indicate the need for further research in this area, bearing in mind the evolution of adversarial attacks and their impact on the future of ML technology.
物体检测是机器学习在图像处理中的一项关键应用，由于深度学习的进步而取得了巨大成功（Girshick 等人，2014 年）。在本文中，我们将重点分析领先的物体检测模型之一 YOLOv5x（Redmon 等人，2016 年）在使用被称为 "对抗性补丁 "的特殊设计干扰（Brown 等人，2017 年）进行对抗性攻击时的脆弱性。这些干扰虽然通常是可见的，但却有能力混淆模型，从而在现实世界的应用中造成严重后果。我们介绍了一种利用各种技术和算法生成这些干扰的方法，并分析了它们在各种条件下的有效性。此外，我们还讨论了针对这些类型攻击的潜在防御措施，并强调了在 ML 技术日益普及的背景下开展安全研究的重要性（Papernot 等人，2016 年）。我们的研究结果表明，考虑到对抗性攻击的演变及其对未来 ML 技术的影响，有必要在这一领域开展进一步研究。
{"title":"When AI Fails to See: The Challenge of Adversarial Patches","authors":"Michał Zimoń, Rafał Kasprzyk","doi":"10.5604/01.3001.0054.0092","DOIUrl":"https://doi.org/10.5604/01.3001.0054.0092","url":null,"abstract":"Object detection, a key application of machine learning in image processing, has achieved significant success thanks to advances in deep learning (Girshick et al. 2014). In this paper, we focus on analysing the vulnerability of one of the leading object detection models, YOLOv5x (Redmon et al. 2016), to adversarial attacks using specially designed interference known as “adversarial patches” (Brown et al. 2017). These disturbances, while often visible, have the ability to confuse the model, which can have serious consequences in real world applications. We present a methodology for generating these interferences using various techniques and algorithms, and we analyse their effectiveness in various conditions. In addition, we discuss potential defences against these types of attacks and emphasise the importance of security research in the context of the growing popularity of ML technology (Papernot et al. 2016). Our results indicate the need for further research in this area, bearing in mind the evolution of adversarial attacks and their impact on the future of ML technology.","PeriodicalId":240434,"journal":{"name":"Computer Science and Mathematical Modelling","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139309808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.5604/01.3001.0053.9736
Małgorzarzata Michniewicz
The development of blockchain technology and distributed ledgers indeed contributes to enabling the delivery of various digital services, such as financial services, registry management, and tokens, including non-fungible tokens (NFTs). In blockchain systems, decisions are made based on the so-called consensus mechanism, which is a method of selecting a single version of transaction history that all nodes consistently agree upon. Although this technology is classified as emerging, it has a history of over ten years, and its ongoing implementations, including in the public administration sector, demonstrate its evolution and its status as one of the most promising technologies in terms of ensuring data immutability. The published ISO (International Organization for Standardization) standards and numerous implementations using business models executed in the DAO (Decentralized Autonomous Organization) architecture undoubtedly support the development of blockchain.
{"title":"Conclusions from the Analysis of Blockchain Solutions","authors":"Małgorzarzata Michniewicz","doi":"10.5604/01.3001.0053.9736","DOIUrl":"https://doi.org/10.5604/01.3001.0053.9736","url":null,"abstract":"The development of blockchain technology and distributed ledgers indeed contributes to enabling the delivery of various digital services, such as financial services, registry management, and tokens, including non-fungible tokens (NFTs). In blockchain systems, decisions are made based on the so-called consensus mechanism, which is a method of selecting a single version of transaction history that all nodes consistently agree upon. Although this technology is classified as emerging, it has a history of over ten years, and its ongoing implementations, including in the public administration sector, demonstrate its evolution and its status as one of the most promising technologies in terms of ensuring data immutability. The published ISO (International Organization for Standardization) standards and numerous implementations using business models executed in the DAO (Decentralized Autonomous Organization) architecture undoubtedly support the development of blockchain.","PeriodicalId":240434,"journal":{"name":"Computer Science and Mathematical Modelling","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139311193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.5604/01.3001.0053.9697
Radosław Kopiński, Karol Antczak
This paper describes an image caption generation system using deep neural networks. The model is trained to maximize the probability of generated sentence, given the image. The model utilizes transfer learning in the form of pretrained convolutional neural networks to preprocess the image data. The datasets are composed of a still photographs and associated with it, five captions in English language. Constructed model is compared to other similarly constructed models using BLEU score system and ways to further improve its performance are proposed.
{"title":"Image caption generation using transfer learning","authors":"Radosław Kopiński, Karol Antczak","doi":"10.5604/01.3001.0053.9697","DOIUrl":"https://doi.org/10.5604/01.3001.0053.9697","url":null,"abstract":"This paper describes an image caption generation system using deep neural networks. The model is trained to maximize the probability of generated sentence, given the image. The model utilizes transfer learning in the form of pretrained convolutional neural networks to preprocess the image data. The datasets are composed of a still photographs and associated with it, five captions in English language. Constructed model is compared to other similarly constructed models using BLEU score system and ways to further improve its performance are proposed.","PeriodicalId":240434,"journal":{"name":"Computer Science and Mathematical Modelling","volume":"116 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139309608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.5604/01.3001.0054.1486
Andrzej Ameljańczyk, Tomasz Ameljańczyk
The article presents the concept of using fuzzy sets methodology in modelling patientʼs disease states for preliminary medical diagnosis. The preliminary medical diagnosis is based on the identified disease symptoms. The basis of the algorithm are descriptions of the patientʼs disease status and patterns of disease entities. These patterns were defined as fuzzy sets. The paper presents simple classifiers that allow he a preliminary diagnosis based on the analysis of fuzzy sets for the use of the general practitioner.
{"title":"Fuzzy sets in modeling patient’s disease states in medical diagnostics support algorithms","authors":"Andrzej Ameljańczyk, Tomasz Ameljańczyk","doi":"10.5604/01.3001.0054.1486","DOIUrl":"https://doi.org/10.5604/01.3001.0054.1486","url":null,"abstract":"The article presents the concept of using fuzzy sets methodology in modelling patientʼs disease states for preliminary medical diagnosis. The preliminary medical diagnosis is based on the identified disease symptoms. The basis of the algorithm are descriptions of the patientʼs disease status and patterns of disease entities. These patterns were defined as fuzzy sets. The paper presents simple classifiers that allow he a preliminary diagnosis based on the analysis of fuzzy sets for the use of the general practitioner.","PeriodicalId":240434,"journal":{"name":"Computer Science and Mathematical Modelling","volume":"31 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139309873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-30DOI: 10.5604/01.3001.0015.8603
O. Dziegielewska
Differential privacy is a statistical disclosure control that is gaining popularity in recent years due to easy application for the data collection mechanisms. Many variants of differential privacy are being developed for specific use cases and environments. One of them is adaptive differential privacy that modulates the generated noise in such a way, that the retrieved result is affected according to the risk profile of the asked query and the risk-accuracy tradeoff required for the queried database. This paper intends to evaluate the adaptive differential privacy using VIOLAS Framework and through assessing how the security characteristics satisfied by the adaptive differential privacy mitigate the risk of selected inference attacks.
{"title":"Evaluating adaptive differential privacy model","authors":"O. Dziegielewska","doi":"10.5604/01.3001.0015.8603","DOIUrl":"https://doi.org/10.5604/01.3001.0015.8603","url":null,"abstract":"Differential privacy is a statistical disclosure control that is gaining popularity in recent years due to easy application for the data collection mechanisms. Many variants of differential privacy are being developed for specific use cases and environments. One of them is adaptive differential privacy that modulates the generated noise in such a way, that the retrieved result is affected according to the risk profile of the asked query and the risk-accuracy tradeoff required for the queried database. This paper intends to evaluate the adaptive differential privacy using VIOLAS Framework and through assessing how the security characteristics satisfied by the adaptive differential privacy mitigate the risk of selected inference attacks.\u0000\u0000","PeriodicalId":240434,"journal":{"name":"Computer Science and Mathematical Modelling","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125497445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-30DOI: 10.5604/01.3001.0015.9040
Paweł Nosażewski, Joanna Wiśniewska
This paper describes the process of designing and implementing a Turing machine simulator application. The created desktop application is distinguished from other solutions by the use of the latest technology and offline operating. The various stages of the project are described, such as defining requirements, creating UML diagrams, and prototyping the user interface. A MVVM architectural model used in building the application is presented. The issues of controls, data binding, and message passing found in the Avalonia package are addressed. The unit tests created and the exploratory tests performed are also described.
{"title":"Implementation of the Turing machine simulator","authors":"Paweł Nosażewski, Joanna Wiśniewska","doi":"10.5604/01.3001.0015.9040","DOIUrl":"https://doi.org/10.5604/01.3001.0015.9040","url":null,"abstract":"This paper describes the process of designing and implementing a Turing machine simulator application. The created desktop application is distinguished from other solutions by the use of the latest technology and offline operating. The various stages of the project are described, such as defining requirements, creating UML diagrams, and prototyping the user interface. A MVVM architectural model used in building the application is presented. The issues of controls, data binding, and message passing found in the Avalonia package are addressed. The unit tests created and the exploratory tests performed are also described.\u0000\u0000","PeriodicalId":240434,"journal":{"name":"Computer Science and Mathematical Modelling","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115897032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-30DOI: 10.5604/01.3001.0015.8604
B. Szafranski
After discussing the function of public registers in the information infrastructure of the State, the paper focuses on the architectural aspects of ensuring the possibility of standardised reference to the services of public registry systems, despite the technological and functional differences between them. Taking this fact into account, the concept was presented to include, in the architecture, the platform for access registry services of an intermediary layer consisting of registry connectors, registry broker and universal registry services, whose (layer) main task is to “mask” the above differences by adapting the services of autonomous registries to the standard required by the main bus of this platform.
{"title":"Registry services and systems - conceptual and architectural aspects","authors":"B. Szafranski","doi":"10.5604/01.3001.0015.8604","DOIUrl":"https://doi.org/10.5604/01.3001.0015.8604","url":null,"abstract":"After discussing the function of public registers in the information infrastructure of the State, the paper focuses on the architectural aspects of ensuring the possibility of standardised reference to the services of public registry systems, despite the technological and functional differences between them. Taking this fact into account, the concept was presented to include, in the architecture, the platform for access registry services of an intermediary layer consisting of registry connectors, registry broker and universal registry services, whose (layer) main task is to “mask” the above differences by adapting the services of autonomous registries to the standard required by the main bus of this platform.\u0000\u0000","PeriodicalId":240434,"journal":{"name":"Computer Science and Mathematical Modelling","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132156623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-30DOI: 10.5604/01.3001.0015.9191
Joanna Wiśniewska, Paweł Wójcik
The following work presents methods of using machine learning to teach a computer to play chess. The first method is based on using records of games played by highly ranked players. The second method is based on the Monte Carlo Tree Search algorithm and reinforcement learning.
{"title":"Machine learning methods in game of chess implementation","authors":"Joanna Wiśniewska, Paweł Wójcik","doi":"10.5604/01.3001.0015.9191","DOIUrl":"https://doi.org/10.5604/01.3001.0015.9191","url":null,"abstract":"The following work presents methods of using machine learning to teach a computer to play chess. The first method is based on using records of games played by highly ranked players. The second method is based on the Monte Carlo Tree Search algorithm and reinforcement learning.\u0000\u0000","PeriodicalId":240434,"journal":{"name":"Computer Science and Mathematical Modelling","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125780156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：