Large language models (LLMs) have been applied to help programming education on aspects such as question answering and program repair. While they make students learn more efficiently, how to use LLMs to help increase ...
详细信息
ISBN:
(纸本)9789819777068;9789819777075
Large language models (LLMs) have been applied to help programming education on aspects such as question answering and program repair. While they make students learn more efficiently, how to use LLMs to help increase teaching efficiency is rarely explored. In this paper, we focus on harnessing LLMs to automatically generate programming exercises with the goal of alleviating teachers' workload and enhancing teaching efficiency. We first evaluate the performance of seven open-source LLMs using prompts, and then fine-tune two winning LLMs using instructions constructed with the Evol-Instruct and the ACES algorithms, respectively. Experimental results demonstrate the improved performance on the two LLMs after the instruction tuning. Additionally, our contribution encompasses the formulation of evaluation metrics and the exploration of various prompt methods.
In most high-risk applications, interpretability is crucial for ensuring system safety and trust. However, existing research often relies on hard-to-understand, highly parameterized models, such as neural networks. In...
详细信息
ISBN:
(纸本)9783031569562;9783031569579
In most high-risk applications, interpretability is crucial for ensuring system safety and trust. However, existing research often relies on hard-to-understand, highly parameterized models, such as neural networks. In this paper, we focus on the problem of policy search in continuous observations and actions spaces. We leverage two graph-based Genetic programming (GP) techniques-Cartesian Genetic programming (CGP) and Linear Genetic programming (LGP)-to develop effective yet interpretable control policies. Our experimental evaluation on eight continuous robotic control benchmarks shows competitive results compared to state-of-the-art Reinforcement Learning (RL) algorithms. Moreover, we find that graph-based GP tends towards small, interpretable graphs even when competitive with RL. By examining these graphs, we are able to explain the discovered policies, paving the way for trustworthy AI in the domain of continuous control.
In a computational complexity theory, P, NP, NP- complete and NP-hard problems are divided into complexity classes which are used to emphasize how challenging it is to solve particular types of problems. The Knapsack ...
详细信息
In a computational complexity theory, P, NP, NP- complete and NP-hard problems are divided into complexity classes which are used to emphasize how challenging it is to solve particular types of problems. The Knapsack problem is a wellknown computational complexity theory and fundamental NP- hard optimization problem that has applications in a variety of disciplines. Being one of the most well-known NP-hard problems, it has been studied extensively in science and practice from theoretical and practical perspectives. One of the solution to the Knapsack problem is the Dantzig's greedy algorithm which can be expressed as a linear programming algorithm which seeks to discover the optimal solution to the knapsack problem. In this paper, an optimized Dantzig greedy (OptDG) algorithm that addresses frequent edge cases, is suggested. Furthermore, OptDG algorithm is compared with the Dantzig's greedy and optimal dynamically programmed algorithms for solving the Knapsack problem and performance evaluation is conducted.
Designing of the function interface is one of the key skills in programming. That requires feedback, which can be generated in the necessary quantity only by an intelligent tutoring system. In this paper, we propose a...
详细信息
ISBN:
(纸本)9783031630279;9783031630286
Designing of the function interface is one of the key skills in programming. That requires feedback, which can be generated in the necessary quantity only by an intelligent tutoring system. In this paper, we propose a method of extracting function descriptions from inline comments in open-source code and find noun phrases that describe the data items passed to and returned from the function. We compare two popular NLP tools for parsing sentences and two different similarity measures to find the best-performing combination and develop sophisticated methods of filtering functions to increase the percentage of correctly marked functions. We achieved correctly marking more than 80% of the automatically selected functions, which significantly speeds up creating banks of learning problems for intelligent tutoring systems in programming learning.
Quantum computing is an emerging field that promises to revolutionize various domains, such as simulation optimization, data processing, and more, by leveraging the principles of quantum mechanics. This paper outlines...
详细信息
ISBN:
(纸本)9798331541378
Quantum computing is an emerging field that promises to revolutionize various domains, such as simulation optimization, data processing, and more, by leveraging the principles of quantum mechanics. This paper outlines innovative pedagogical strategies developed by university lecturers in Finland and Spain for teaching quantum computerprogramming and quantum software engineering. Our curriculum integrates essential tools and methodologies such as containerization with Docker, Qiskit, PennyLane, and Ocean SDK to provide a comprehensive learning experience. The approach consists of several steps, from introducing the fundamentals of quantum mechanics to hands-on labs focusing on practical use cases. We believe quantum computerprogramming is an important topic and one that is hard to teach, so having a teaching agenda and guidelines for teaching can be of great help.
Online judges in programming courses allow students to improve their coding abilities and instructors to analyze student work and detect challenging topics. Although several online judge platforms are available, most ...
详细信息
ISBN:
(纸本)9798400704239
Online judges in programming courses allow students to improve their coding abilities and instructors to analyze student work and detect challenging topics. Although several online judge platforms are available, most are limited in that they cannot support a large number of students simultaneously working on an assignment during a fixed time period, or can only do so at a significant cost, making the use of such systems in developing countries non-viable. This paper presents Clearn, a new platform that is (1) cost-conscious, as we have focused on lowering costs, (2) student-led, as we have empowered students and teaching assistants to lead its development and maintenance, and (3) highly simultaneous, as it allows over 1,000 students to work simultaneously on a timed assignment. This paper presents the platform, as well as the lessons learned during its development and deployment, and its reception by the students.
Quantum programming presents a significant departure from traditional programming due to its non-intuitive algorithm design and reliance on intricate linear algebraic derivations. Therefore, formal verification using ...
详细信息
ISBN:
(数字)9789819723409
ISBN:
(纸本)9789819723393;9789819723409
Quantum programming presents a significant departure from traditional programming due to its non-intuitive algorithm design and reliance on intricate linear algebraic derivations. Therefore, formal verification using theorem provers is essential and highly suitable for quantum programming. The mathematical foundation of quantum computing lies in matrix and vector computation. Hence, establishing a proper formal theory of matrices and vectors within theorem provers becomes of utmost significance. This paper expands and refines a Coq-based type system tailored for quantum computing, focusing specifically on powers-of-2 matrices and vectors. This enables precise descriptions of quantum states and operations while facilitating the formal verification of quantum programs. By utilizing this type system, we offer an environment for writing and verifying quantum programs. The verified programs can be extracted as equivalent OCaml files and executable simulators. Our work provides an effective infrastructure for quantum programming, verification and simulation, thereby laying a foundation for future developments.
Reversible programming languages guarantee that their programs are invertible at the cost of restricting the permissible operations to those which are locally invertible. However, writing programs in a reversible styl...
详细信息
ISBN:
(纸本)9783031620751;9783031620768
Reversible programming languages guarantee that their programs are invertible at the cost of restricting the permissible operations to those which are locally invertible. However, writing programs in a reversible style can be cumbersome, and may produce significantly different implementations than the conventional - even when the implemented algorithm is, in fact, invertible. We introduce Jeopardy, a functional programming language that guarantees global program invertibility without imposing local invertibility. In particular, Jeopardy allows the limited use of uninvertible - and even nondeterministic - operations, provided that they are used in a way that can be statically determined to be globally invertible. To this end, we outline an implicitly available arguments analysis and further approaches that can give a partial static guarantee to the (generally difficult) problem of guaranteeing invertibility.
This paper introduces a Multi-Aspect Visualization Framework, a language-agnostic interactive platform designed to enhance programming education by addressing the unique challenges and opportunities inherent in the fi...
详细信息
programming courses in higher education are often attended by several hundred students. In such large-scale courses, direct instruction is often the last resort, resulting in mostly passive students and limited social...
详细信息
ISBN:
(纸本)9798400706004
programming courses in higher education are often attended by several hundred students. In such large-scale courses, direct instruction is often the last resort, resulting in mostly passive students and limited social interaction. The instructor may present worked examples or perform live coding and the students try to reproduce these on their devices. However, there is usually no live coding where students work on small programming assignments themselves directly in class, because the instructor does not have a timely/rapid overviewof the most important common issues that are prevalent in class to support the students. This paper presents experiences with a teaching format to activate students that addresses the aforementioned issues. After students have worked on a small assignment and uploaded their solution attempt within a specified time period, an extended e-assessment system analyzes all submissions and instantly provides an overview of the number of correct submissions as well as all common errors and their frequency to assist the instructor in the immediate tailored discussion. This approach makes it possible to engage students, make student performance visible to all participants, and discuss the most common errors. Students liked "their" live coding, the discussion of "their" errors, and want to do it more often, although not many students uploaded their solution attempts. The teaching scenario, benefits, pitfalls, possible improvements, and further application scenarios are discussed.
暂无评论