In current machine learning research, deep learning methodologies have become the prevalent approach across various domains, including decision-making processes. However, the interpretability of solutions generated by...
详细信息
ISBN:
(纸本)9783031611391;9783031611407
In current machine learning research, deep learning methodologies have become the prevalent approach across various domains, including decision-making processes. However, the interpretability of solutions generated by these algorithms remains a significant challenge, as these models do not inherently prioritize explainability. This lack of interpretability hampers the analysis of decision-making rationales. One potential remedy to this issue is the employment of Genetic Network programming (GNP), a method within the evolutionary computing paradigm, known for its ability to generate more interpretable solutions. This study provides a concise overview of GNP, exploring its modifications and applications to demonstrate its utility in addressing the interpretability challenge in machine learning algorithms.
Contribution: Understanding pupils' conceptualization of robots and programming can help teachers to avoid a disconfirmation experience by selecting more appropriate educational tools, robot designers in improving...
详细信息
Contribution: Understanding pupils' conceptualization of robots and programming can help teachers to avoid a disconfirmation experience by selecting more appropriate educational tools, robot designers in improving the robot design, and researchers in further improvement of the field. Background: Human-robot interaction (HRI) is affected by the actual but also expected robot's appearance and capabilities. Multiple factors, such as age, gender, media exposure, ICT exposure, or culture, influence mental models regarding robots;therefore, it is important to investigate those for a specific cohort in the designated geographical area. Research Questions: The mental models regarding robots and programming, and the way they are possibly biased by popular culture, exposure to ICT or parental influence were studied. Research questions concerned cognitive elements of mental models, namely, definitions and knowledge of robots, and programming and how those progress in time. Also, the research studied a figurative aspect of mental models regarding robots, with a focus on anthropomorphic features. Methodology: To research the influence of the short-term HRI, four classes of eight to nine years old elementary school pupils were included in a workshop where pre and postquestionnaires were used as research instruments. Besides pupils, later in this two-phase longitudinal research, after a year of formal education in Informatics, research instruments also included teachers and parents, to investigate their influence on children's mental models. Findings: The change of mental models under the influence of the one-time workshop was not permanent. However, a combination of maturation with informal and formal intervention supports the conceptualization of programming.
One of the important roles of educators and academicians is to accurately assess students, and provide timely feedback to ensure that the learning outcomes of the academic program are achieved. Student performance pre...
详细信息
ISBN:
(数字)9798350367355
ISBN:
(纸本)9798350367355
One of the important roles of educators and academicians is to accurately assess students, and provide timely feedback to ensure that the learning outcomes of the academic program are achieved. Student performance prediction can help in this regard by predicting the future performance of the student based on the student's past performance benefitting from the data availability in the learning management system of the academic institution. This work aims to implement a machine learning model to predict the performance of students;particularly, students in the computerscience and Engineering majors, based on their past performance in general first-year courses, namely, English, Math, and programming. These particular courses were selected for the prediction purpose because they are essential in the academic progress of students in the computerscience and Engineering majors. Specifically, English is the study language, yet it is considered a second language for many students, which can pose challenges in perceiving the core technical courses. Besides, Math and programming courses are essential to understand the technical aspects of most computerscience and Engineering courses. Therefore, knowing how the student is performing in these first-year courses will give important insights on how the student will perform later in the study program. In this work, the student performance is indicated by the Cumulative Grade Point Average (CGPA) which is predicted using polynomial regression based on a real dataset. The utilized dataset includes information about the CGPA and the grades of English, Math, and programming courses from different levels (i.e., fresh and senior students), and extracted from the learning and management system of an academic institution. It is worth to mention that different degrees of the polynomial regression were investigated to observe how well the curve fits the data. To evaluate the prediction performance, the R-squared value is used. Results sh
In this paper, we establish the computational complexities of selected forms of refutations of linear programs. Linear programming is in the complexity class P and hence, it must have short affirmative and disqualifyi...
详细信息
ISBN:
(纸本)9783031637346;9783031637353
In this paper, we establish the computational complexities of selected forms of refutations of linear programs. Linear programming is in the complexity class P and hence, it must have short affirmative and disqualifying certificates. One of the more celebrated lemmata in linear programming is Farkas' lemma, which establishes that both "yes" and "no" certificates can be thought of as solutions to complementary linear programs. Since then, it has been established that if a linear program is feasible, then it must have a solution which is bounded by a polynomial function of the input size. The latter observation, coupled with Farkas' lemma, immediately establishes that linear programming is in NP boolean AND coNP. Our goal is to study the computational complexities of determining various constrained refutations for a given linear programming problem. This paper focuses on three distinct refutation forms, viz., read-once, tree-like and dag-like. We establish that checking if a linear program has a read-once refutation is NP-complete, even when it is defined by Binary Two Variable Per Inequality (BTVPI) constraints. Furthermore, the problems of finding the shortest tree-like and dag-like refutations are NPO-complete and NPO PB-complete respectively.
This Innovative Practice Full Paper presents our design of teaching computerprogramming for middle and high school students during an one-week Summer camp for the past five years, with an interruption in the Summer o...
详细信息
ISBN:
(纸本)9798350336429
This Innovative Practice Full Paper presents our design of teaching computerprogramming for middle and high school students during an one-week Summer camp for the past five years, with an interruption in the Summer of 2020 due to the Covid-19 pandemic. Many researchers believe that good Summer camps can improve many students' educational and career development outcomes. Teachers and administrators are increasingly promoting Summer camp opportunities for introducing programming skills to middle and high school students. The motivation of our program is to offer hands-on projects for middle and high school students to increase their interests and knowledge in computing to meet the growing demand. Like some Summer coding camps, we picked Scratch as the programming language (designed and offered for free by the Massachusetts Institute of Technology) for the students to learn important mathematical and computerprogramming concepts. In addition, the students learn how to think and reason creatively, reason systematically, and work collaboratively, while also having fun during the one-week Summer camp. For the students already familiar with Scratch, the instructor exposed students to basic concepts of Java programming language, such as Java virtual machine, computer memory, data representation, primitive data types, casting, arithmetic, and relational operators, as well as the assignment, selection and printing statements. This article presents our findings from Summer camps organized in 2018 and 2022. Our conclusion is that all students showed a better understanding of programming concepts and confidence in computing. In the upcoming paper sections, we will describe details about how we made one-week camps to be unique compared to other similar camps. One element of our own approach is to teach in an effective and innovative using an interactive teaching approach. For example, when we designed the lecture notes, we imagine that we are students taking for the first time
In this paper, we investigate the influence of various factors, such as programming language, testing environment, and input data, on the accuracy of algorithm execution measurements. To conduct this study, we used th...
详细信息
A Low-rank Spectral Optimization Problem (LSOP) minimizes a linear objective function subject to multiple two-sided linear inequalities intersected with a low-rank and spectral constrained domain. Although solving LSO...
详细信息
ISBN:
(纸本)9783031598340;9783031598357
A Low-rank Spectral Optimization Problem (LSOP) minimizes a linear objective function subject to multiple two-sided linear inequalities intersected with a low-rank and spectral constrained domain. Although solving LSOP is, in general, NP-hard, its partial convexification (i.e., replacing the domain by its convex hull) termed "LSOP-R", is often tractable and yields a high-quality solution. This motivates us to study the strength of LSOP-R. Specifically, we derive rank bounds for any extreme point of the feasible set of LSOP-R with different matrix spaces and prove their tightness. The proposed rank bounds recover two well-known results in the literature from a fresh angle and allow us to derive sufficient conditions under which the relaxation LSOP-R is equivalent to LSOP. To effectively solve LSOP-R, we develop a column generation algorithm with a vector-based convex pricing oracle, coupled with a rank-reduction algorithm, which ensures that the output solution always satisfies the theoretical rank bound. Finally, we numerically verify the strength of LSOP-R and the efficacy of the proposed algorithms.
programming is a fundamental subject in the majority of technology-oriented degrees, particularly in computer Engineering programs. Mastering programming requires continuous practice to understand the syntax, semantic...
详细信息
This paper introduces Zweistein, a dynamic programming evaluation function for Einstein Würfelt Nicht! (EWN). Instead of relying on human knowledge to craft an evaluation function, Zweistein uses a data-centric a...
详细信息
We focus on the evolutionary design of programs capable of capturing more randomness and outliers in the input data set than the standard genetic programming (GP)-based methods typically allow. We propose Genetic Prog...
详细信息
ISBN:
(纸本)9783031295720;9783031295737
We focus on the evolutionary design of programs capable of capturing more randomness and outliers in the input data set than the standard genetic programming (GP)-based methods typically allow. We propose Genetic programming with Associative Memory (GPAM) - a GP-based system for symbolic regression which can utilize a small associative memory to store various data points to better approximate the original data set. The method is evaluated on five standard benchmarks in which a certain number of data points is replaced by randomly generated values. In another case study, GPAM is used as an on-chip generator capable of approximating the weights for a convolutional neural network (CNN) to reduce the access to an external weight memory. Using Cartesian genetic programming (CGP), we evolved expression-memory pairs that can generate weights of a single CNN layer. If the associative memory contains 10% of the original weights, the weight generator evolved for a convolutional layer can approximate the original weights such that the CNN utilizing the generated weights shows less than a 1% drop in the classification accuracy on the MNIST data set.
暂无评论