scholarly journals Developing a Conversational Agent to Explore Machine Learning Concepts

2021 ◽  
Vol 21 ◽  
pp. 26-34
Author(s):  
Ayse Kok Arslan

This study aims to introduce a discussion platform and curriculum designed to help people understand how machines learn. Research shows how to train an agent through dialogue and understand how information is represented using visualization. This paper starts by providing a comprehensive definition of AI literacy based on existing research and integrates a wide range of different subject documents into a set of key AI literacy skills to develop a user-centered AI. This functionality and structural considerations are organized into a conceptual framework based on the literature. Contributions to this paper can be used to initiate discussion and guide future research on AI learning within the computer science community.

2021 ◽  
Author(s):  
Ayse Kok Arslan

This study aims to introduce a discussion platform and curriculum designed to help people understand how machines learn. Research shows how to train an agent through dialogue and understand how information is represented using visualization. This paper starts by providing a comprehensive definition of AI literacy based on existing research and integrates a wide range of different subject documents into a set of key AI literacy skills to develop a user-centered AI. This functionality and structural considerations are organized into a conceptual framework based on the literature. Contributions to this paper can be used to initiate discussion and guide future research on AI learning within the computer science community.


2021 ◽  
Vol 8 (3) ◽  
pp. 1-14
Author(s):  
Ayse Kok Arslan

This study aims to introduce a discussion platform and curriculum designed to help people understand how machines learn. Research shows how to train an agent through dialogue and understand how information is represented using visualization. This paper starts by providing a comprehensive definition of AI literacy based on existing research and integrates a wide range of different subject documents into a set of key AI literacy skills to develop a user-centered AI. This functionality and structural considerations are organized into a conceptual framework based on the literature. Contributions to this paper can be used to initiate discussion and guide future research on AI learning within the computer science community.


2020 ◽  
Author(s):  
Sina Faizollahzadeh Ardabili ◽  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Filip Ferdinand ◽  
Annamaria R. Varkonyi-Koczy ◽  
...  

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models needs to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to SIR and SEIR models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. Paper further suggests that real novelty in outbreak prediction can be realized through integrating machine learning and SEIR models.


2020 ◽  
Author(s):  
Xiaojie Guo ◽  
Liang Zhao

Graphs are important data representations for describing objects and their relationships, which appear in a wide diversity of real-world scenarios. As one of a critical problem in this area, graph generation considers learning the distributions of given graphs and generating more novel graphs. Owing to its wide range of applications, generative models for graphs have a rich history, which, however, are traditionally hand-crafted and only capable of modeling a few statistical properties of graphs. Recent advances in deep generative models for graph generation is an important step towards improving the fidelity of generated graphs and paves the way for new kinds of applications. This article provides an extensive overview of the literature in the field of deep generative models for graph generation. Firstly, the formal definition of deep generative models for the graph generation as well as preliminary knowledge is provided. Secondly, two taxonomies of deep generative models for unconditional, and conditional graph generation respectively are proposed; the existing works of each are compared and analyzed. After that, an overview of the evaluation metrics in this specific domain is provided. Finally, the applications that deep graph generation enables are summarized and five promising future research directions are highlighted.


2019 ◽  
Vol 296 ◽  
pp. 3-8
Author(s):  
David Bujdoš ◽  
Lucia Bulíková

Nowadays, the colouring is used in wide range of architectural concrete. Therefore, determination efficiency of pigments in case of particular combination of input materials is necessary. The research deals with influence of concentration of liquid inorganic pigments on the resulting colour of cement mortars. Two liquid pigments (yellow, red) were used for measurement purposes to verify their optimal ratio to achieve the best colouring of cement specimens. Pigments were mixed in the mortars of two types of cements used for architectural and decorative design. The colour change was determined using Konica Minolta spectrophotometer in colour space CIE Lab (1976). General definition of deviation in the colour space ΔELab was applied for calculating of colour deviation. From the results of the laboratory tests is obvious that significant change of the colour of cement specimens do not show between the concentration of 6% and 9% of the pigment per cement weight yet. Consequently, using of high ratio of pigment than 9% is not profitable neither for purchaser, nor builder. Future research will focus on trials with a more elaborate share of pigment and it will have importance for price optimization in the construction industry.


2021 ◽  
Vol 13 (18) ◽  
pp. 10048
Author(s):  
Benjamin Gidron ◽  
Yael Israel-Cohen ◽  
Kfir Bar ◽  
Dalia Silberstein ◽  
Michael Lustig ◽  
...  

The Impact Tech Startup (ITS) is a new, rapidly developing type of organizational category. Based on an entrepreneurial approach and technological foundations, ITSs adopt innovative strategies to tackle a variety of social and environmental challenges within a for-profit framework and are usually backed by private investment. This new organizational category is thus far not discussed in the academic literature. The paper first provides a conceptual framework for studying this organizational category, as a combination of aspects of social enterprises and startup businesses. It then proposes a machine learning (ML)-based algorithm to identify ITSs within startup databases. The UN’s Sustainable Development Goals (SDGs) are used as a referential framework for characterizing ITSs, with indicators relating to those 17 goals that qualify a startup for inclusion in the impact category. The paper concludes by discussing future research directions in studying ITSs as a distinct organizational category through the usage of the ML methodology.


2016 ◽  
Vol 23 (3) ◽  
pp. 145-149
Author(s):  
Marek Żukowicz ◽  
Michał Markiewicz

Abstract The aim of the article is to present a mathematical definition of the object model, that is known in computer science as TreeList and to show application of this model for design evolutionary algorithm, that purpose is to generate structures based on this object. The first chapter introduces the reader to the problem of presenting data using the TreeList object. The second chapter describes the problem of testing data structures based on TreeList. The third one shows a mathematical model of the object TreeList and the parameters, used in determining the utility of structures created through this model and in evolutionary strategy, that generates these structures for testing purposes. The last chapter provides a brief summary and plans for future research related to the algorithm presented in the article.


2020 ◽  
Author(s):  
Sina Faizollahzadeh Ardabili ◽  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Filip Ferdinand ◽  
Annamaria R. Varkonyi-Koczy ◽  
...  

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models needs to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to SIR and SEIR models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. Paper further suggests that real novelty in outbreak prediction can be realized through integrating machine learning and SEIR models.


Author(s):  
Kateryna Osadcha ◽  
Hanna Chemerys

The article is devoted to theoretical analysis of the value of graphic competence. The basic scientific positions concerning the formation of graphic competence as an important component of the professional formation of specialists in the system of higher education of Ukraine are considered. The analysis of modern approaches, highlighted in domestic sources, concerning the definition of the essence of the concept of "graphic competence" as a component of qualitative training of a specialist has been carried out. The author emphasizes the demand for the formation of graphic culture in the future bachelors of computer sciences, on the basis of which the author's view on the definition of graphic competence as a component of qualitative professional training of competitive future bachelors on computer sciences in the conditions of a pedagogical institution of higher education taking into account modern social processes. The urgency of forming graphic competence is also substantiated by its role in education, development and upbringing, namely, in the development of thinking, cognitive abilities and spatial imagination of future bachelors in computer sciences, the development of practical skills. Due to the fact that the target preparation of the Bachelor of Computer Science is aimed at training highly skilled professionals, then each graduate of this profile must have a wide range of basic knowledge, skills and abilities in computer graphics and design for effective presentation of the developed Software to the end user. In order to develop the graphic competence of future bachelors in computer sciences, their training should be based on the development of basic knowledge of students on systems of computer design and graphics, computer animation and visualization, and work with graphical packages of 3D design. This will ensure conditions for the graduate to adapt to their professional activities and the subsequent successful application of acquired skills. The results of the analysis of the scientific experience of the mentioned authors, we have determined that graphic competence is versatile, and includes not only the features inherent in artistic or creative activity, but also solid knowledge and skills of the technical component, which are rapidly expanding and branching in view of rapid pace of development of computer technology and modernization of graphic tools.


2020 ◽  
Author(s):  
Sina F. Ardabili ◽  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Filip Ferdinand ◽  
Annamaria R. Varkonyi-Koczy ◽  
...  

Abstract Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models needs to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to susceptible-infected-recovered (SIR) and susceptible-exposed-infectious-recovered (SEIR) models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. Paper further suggests that real novelty in outbreak prediction can be realized through integrating machine learning and SEIR models.


Sign in / Sign up

Export Citation Format

Share Document