When developing empirical equations, domain experts require these to be accurate and adhere to physical laws. Often, constants with unknown units need to be discovered alongside the equations. Traditional unit-aware g...
详细信息
ISBN:
(纸本)9783031700545;9783031700552
When developing empirical equations, domain experts require these to be accurate and adhere to physical laws. Often, constants with unknown units need to be discovered alongside the equations. Traditional unit-aware genetic programming (GP) approaches cannot be used when unknown constants with undetermined units are included. This paper presents a method for dimensional analysis that propagates unknown units as "jokers" and returns the magnitude of unit violations. We propose three methods, namely evolutive culling, a repair mechanism, and a multi-objective approach, to integrate the dimensional analysis in the GP algorithm. Experiments on datasets with ground truth demonstrate comparable performance of evolutive culling and the multi-objective approach to a baseline without dimensional analysis. Extensive analysis of the results on datasets without ground truth reveals that the unit-aware algorithms make only low sacrifices in accuracy, while producing unit-adherent solutions.
Computational thinking (CT) is an essential skill required for every individual in the digital era to become creative problem solvers. The purpose of this research is to investigate the relationships between computati...
详细信息
Computational thinking (CT) is an essential skill required for every individual in the digital era to become creative problem solvers. The purpose of this research is to investigate the relationships between computational thinking skills, the Big Five personality factors, and learning motivation using structural equation modeling (SEM). The research administered the computational thinking scale, NEO FFI scale, and Motivated Strategies for Learning Questionnaire to a sample of 92 students pursuing degrees in computerscience and Engineering. Based on the result analysis, it was determined that both personality and learning motivation had positive and significant impacts on computation thinking skills. Personality had a major contribution to the prediction of CT, with consciousness being the most influential predictor. The findings of this study suggest that educators and academics should focus on the significance of the psychological side of CT for the improvement of students' CT skills.
Block-based programming is an effective way to introduce students to computerscienceprogramming [3], [7], [8]. As the researcher community keeps lowering the barrier to entry, BBP environments now support learners a...
详细信息
Genetic programming-based evolutionary feature construction is a widely used technique for automatically enhancing the performance of a regression algorithm. While it has achieved great success, a challenging problem ...
详细信息
ISBN:
(纸本)9783031569562;9783031569579
Genetic programming-based evolutionary feature construction is a widely used technique for automatically enhancing the performance of a regression algorithm. While it has achieved great success, a challenging problem in feature construction is the issue of overfitting, which has led to the development of many multi-objective methods to control overfitting. However, for multi-objective methods, a key issue is how to select the final model from the front with different trade-offs. To address this challenge, in this paper, we propose a novel minimal complexity knee point selection strategy in evolutionary multi-objective feature construction for regression to select the final model for making predictions. Experimental results on 58 datasets demonstrate the effectiveness and competitiveness of this strategy when compared to eight existing methods. Furthermore, an ensemble of the proposed strategy and existing model selection strategies achieves the best performance and outperforms four popular machine learning algorithms.
Block-based programming environments, widely used for teaching beginners, pose accessibility challenges for individuals with visual impairments due to limited support for screen readers and keyboard navigation. To add...
详细信息
In this paper, we propose a new approach for the top-down compilation of relaxed Binary Decision Diagrams (BDDs) for Discrete Optimization: Lookahead, Merge and Reduce. The approach is inspired by the bottom-up algori...
详细信息
ISBN:
(数字)9783031605994
ISBN:
(纸本)9783031606014;9783031605994
In this paper, we propose a new approach for the top-down compilation of relaxed Binary Decision Diagrams (BDDs) for Discrete Optimization: Lookahead, Merge and Reduce. The approach is inspired by the bottom-up algorithm for reducing exact BDDs in which equivalent nodes, that is, nodes with the same partial completions, are merged. In our top-down compilation approach, we apply this reduction algorithm for determining which states to be merged by constructing a lookahead layer, merging the lookahead layer nodes according to some heuristic and then deeming nodes having the same feasible completions in the lookahead BDD as approximately equivalent. Moreover, under certain structural properties we prove an upper limit on the size of the reduced layers given the size of the merged lookahead layer. In a set of preliminary computational experiments, we evaluate our approach for the 0/1 Knapsack problem, showing that the approach often achieves much stronger bounds than the traditional top-down compilation scheme.
Foundational language models, i.e. large, pre-trained neural transformer models like Google BERT and OpenAI ChatGPT, GPT-3 or GPT-4 have created considerable general media attention. Microsoft's *** service has al...
详细信息
ISBN:
(纸本)9783031504846;9783031504853
Foundational language models, i.e. large, pre-trained neural transformer models like Google BERT and OpenAI ChatGPT, GPT-3 or GPT-4 have created considerable general media attention. Microsoft's *** service has also integrated a foundational model (CodePilot) to make programmers more productive. Some people have gone so far and heralded the end of the programming profession, an unsubstantiated claim. We investigate the research question to what extent individuals without the necessary technical background can still use such systems to achieve a set task. Our single case study based preliminary evidence suggests that using such systems may lead to a good task completion rate, but without deepening the understanding much on the way.
In the dynamic educational context of Malaysia, this study examines the impact of integrating Unplugged Activities (UA) with Block-Based programming (BBP) on improving the computational thinking (CT) skills of seconda...
详细信息
In the dynamic educational context of Malaysia, this study examines the impact of integrating Unplugged Activities (UA) with Block-Based programming (BBP) on improving the computational thinking (CT) skills of secondary students in full boarding schools in Northern Peninsular Malaysia. Using a quasi-experimental design and mixed-methods analysis, the research evaluates the impact of these teaching methods on students' CT skills and attitudes toward programming. This research compares the results between a group that uses only BBP and another that combines both UA and BBP. The results indicate that CT skills improved in both groups, while students in the UA + BBP group showed more significant gains in confidence and a more positive attitude toward programming. These results provide valuable insights into pedagogical strategies within digital education and highlight the benefits of an integrated approach that combines tactile learning experiences with digital technologies. By combining hands-on activities with technology-based instruction, this approach not only deepens students' understanding of CT concepts but also positively changes their perception and engagement with programming.
State-of-the-art large language models (LLMs) have demonstrated an extraordinary ability to write computer code. This ability can be quite beneficial when integrated into an IDE to assist a programmer with basic codin...
详细信息
ISBN:
(纸本)9798400705793
State-of-the-art large language models (LLMs) have demonstrated an extraordinary ability to write computer code. This ability can be quite beneficial when integrated into an IDE to assist a programmer with basic coding. On the other hand, it may be misused by computerscience students for cheating on coding tests or homework assignments. At present, knowledge about the exact capabilities and limitations of state-of-the-art LLMs is still inadequate. Furthermore, their capabilities have been changing quickly with each new release. In this paper, we present a dataset of 559 programming exercises in 10 programming languages collected from a system for evaluating coding assignments at our university. We have experimented with four well-known LLMs (GPT-3.5, GPT-4, Codey, Code Llama) and asked them to solve these assignments. The evaluation results are intriguing and provide insights into the strengths and weaknesses of the models. In particular, GPT-4 (which performed the best) is currently capable of solving 55% of all our exercises and achieved an average score of 86% on exercises from the introductory programming course (using the best of five generated solutions).
This study investigates the implementation and impact of mastery learning in a computerscience course, particularly during the transition from traditional teaching methods to mastery learning amidst the COVID-19 pand...
详细信息
暂无评论