The increased emphasis on competency management and learning objectives in higher education has led to a rise in Learning Analytics (LA) applications. These tools play a vital role in measuring and optimizing learning...
详细信息
Our study presents a strategy for designing and implementing a Multi-Agent System (MAS) using organizational paradigms. The developed system offers a healthcare-oriented approach that utilizes the Internet of Medical ...
详细信息
This paper tackles the challenge of symbolic regression (SR) with a vast mathematical expression space, where the primary difficulty lies in accurately identifying subspaces that are more likely to contain the correct...
详细信息
ISBN:
(纸本)9783031700545;9783031700552
This paper tackles the challenge of symbolic regression (SR) with a vast mathematical expression space, where the primary difficulty lies in accurately identifying subspaces that are more likely to contain the correct mathematical expressions. Establishing the NP-hard nature of the SR problem, this study introduces a novel approach named Symbol Graph Genetic programming (SGGP) (Code is available at https://***/SymbolGraph/sggp). SGGP begins by constructing a symbol graph to represent the mathematical expression space effectively. It then employs the generalized Pareto distribution based on semantic similarity to assess the likelihood that each edge (subspace) in this graph will yield superior individuals. Guided by these probabilistic evaluations, SGGP strategically samples new individuals in its quest to discover accurate mathematical expressions. Comparative experiments conducted across three different benchmark types demonstrate that SGGP outperforms 21 existing baseline SR methods, achieving greater accuracy and conciseness in the mathematical expressions it generates.
Enbugging quiz is a format of programming exercises that let learners edit a given program so that it yields a designated error message. In order to formulate a quiz problem with less ambiguity and reasonable difficul...
详细信息
In recent years an interest has sparked in universities to enhance student learning in introductory programming courses that go beyond the traditional learning methods. Therefore, it was in our interest to investigate...
In recent years an interest has sparked in universities to enhance student learning in introductory programming courses that go beyond the traditional learning methods. Therefore, it was in our interest to investigate whether template-based programming questions are more effective for learning programming concepts compared to reading literature. This was investigated by firstly, dividing a group of students into a theory group and a program-tracing group. Each group then did an initial test. Afterwards, the program-tracing group received code- tracing problems and the theory group received literature covering programming concepts. Both groups used their resources to practise for a final test. Finally, both groups did the final test. The results from the initial test and the final test was compared, however, the results were not conclusive as there was too little data due to multiple factors. It was also concluded that this study can be further developed if it was part of a course. Under de senaste åren har ett intresse utvecklats bland universiten i att förbättra studenternas lärande i introducerande programmeringskurser genom att gå utöver de traditionella inlärningsmetoderna. Därför var det i vårt intresse att undersöka om mallbaserade programmeringsfrågor är mer effektiva för att lära sig programmeringskoncept jämfört med att läsa litteratur. Detta undersöktes genom att först dela en grupp elever i en teorigrupp och en programspårningsgrupp. Sedan gjorde varje grupp ett första test. Där efter fick programspårningsgruppen kodspårningsproblem och teorigruppen fick litteratur som omfattar programmeringskoncept. Sedan använde båda grupperna sina resurser för att öva för ett slutligt test. Efter det slutgiltiga testet jämfördes resultaten från det initiala testet och det slutliga testet, men resultaten gav inte upphov till några slutsatser eftersom inte fanns tillräckligt med data på grund av olika faktorer. Denna studie kan vidareutvecklas genom att vara en del av
Universal probabilistic programming languages (PPLs) make it relatively easy to encode and automatically solve statistical inference problems. To solve inference problems, PPL implementations often apply Monte Carlo i...
详细信息
ISBN:
(纸本)9783031572661;9783031572678
Universal probabilistic programming languages (PPLs) make it relatively easy to encode and automatically solve statistical inference problems. To solve inference problems, PPL implementations often apply Monte Carlo inference algorithms that rely on execution suspension. State-of-the-art solutions enable execution suspension either through (i) continuation-passing style (CPS) transformations or (ii) efficient, but comparatively complex, low-level solutions that are often not available in high-level languages. CPS transformations introduce overhead due to unnecessary closure allocations-a problem the PPL community has generally overlooked. To reduce overhead, we develop a new efficient selective CPS approach for PPLs. Specifically, we design a novel static suspension analysis technique that determines parts of programs that require suspension, given a particular inference algorithm. The analysis allows selectively CPS transforming the program only where necessary. We formally prove the correctness of the analysis and implement the analysis and transformation in the Miking CorePPL compiler. We evaluate the implementation for a large number of Monte Carlo inference algorithms on real-world models from phylogenetics, epidemiology, and topic modeling. The evaluation results demonstrate significant improvements across all models and inference algorithms.
We consider a Job Shop Scheduling Problem with transport (JSPT) which consists in jointly scheduling machines and robots. In contrast with the literature, we assume that a transport operation may involve several robot...
详细信息
ISBN:
(纸本)9783031629112;9783031629129
We consider a Job Shop Scheduling Problem with transport (JSPT) which consists in jointly scheduling machines and robots. In contrast with the literature, we assume that a transport operation may involve several robots simultaneously, which requires resource synchronization over time. We formulate this problem as a Mixed Integer Linear programming (MILP) formulation. Then we propose a GRASP-ELS meta-heuristic and a local search procedure where we use a Bierwith's sequence approach to evaluate a solution. In a numerical study, we have adapted instances from the literature to our problem. The meta-heuristic competes with the exact resolution providing high quality solution in reduced computation time, which lead us to consider that both the modeling and local search are accurate.
Neural network verification aims at providing formal guarantees on the output of trained neural networks, to ensure their robustness against adversarial examples and enable deployment in safety-critical applications. ...
详细信息
ISBN:
(纸本)9783031606014;9783031605994
Neural network verification aims at providing formal guarantees on the output of trained neural networks, to ensure their robustness against adversarial examples and enable deployment in safety-critical applications. This paper introduces a new approach to neural network verification using a novel mixed-integer programming (MIP) rolling-horizon decomposition method. The algorithm leverages the layered structure of neural networks by employing optimization-based bound tightening (OBBT) on smaller sub-graphs of the original network in a rolling-horizon fashion and tightening the bounds in parallel. This strategy strikes a balance between achieving tighter bounds and ensuring the tractability of the underlying mixed-integer programs. Extensive numerical experiments, conducted on instances from the VNN-COMP benchmark library, demonstrate that the proposed approach yields significantly improved bounds compared to existing efficient bound propagation methods. Notably, the proposed method proves effective in solving open verification problems. Our code is built and released as part of the open-source mathematical modeling tool Gravity (https://***/ coin- or/Gravity), which is extended to support generic neural network models.
While many recent studies have explored how large language models can transform computerscience instruction from the instructor perspective, they are primarily at the college level. Thus, little is known about using ...
详细信息
ISBN:
(纸本)9798400705311
While many recent studies have explored how large language models can transform computerscience instruction from the instructor perspective, they are primarily at the college level. Thus, little is known about using large language models towards curriculum development and teacher supports outside of the college setting. Given the emphasis placed on culturally responsive teaching at the K-8 level and well-documented evidence of insensitive and inaccurate language model outputs from a cultural perspective, it is imperative to perform systematic and principled research before considering their use in this setting. This paper explores the potential of teachers using large language models to brainstorm instructional Scratch projects. Specifically, we use GPT-3 to mimic structured projects from an existing computerscience curriculum but situate the generated projects in different contexts/themes. We qualitatively analyze 300 project ideas generated by GPT and find 81% of the generated ideas satisfy our metrics for technical alignment and theme quality. We identify two major weaknesses: code complexity of generated projects and presence of potential insensitive elements that would require human filtering. We conclude that, while not ready as a studentfacing solution, teachers could use GPT to effectively brainstorm customized instructional materials.
programming is a fundamental aspect of engineering and science that requires both knowledge and skills in programming. It is generally accepted that the more learners practice programming, the better their skills are....
详细信息
暂无评论