The circular economy represents a critical pathway toward achieving sustainable development goals through responsible resource production and consumption. Monitoring progress toward implementing a circular economy in ...
详细信息
The rapid progress of AI-powered programming assistants, such as GitHub Copilot, has facilitated the development of software applications. These assistants rely on large language models (LLMs), which are foundation mo...
详细信息
ISBN:
(纸本)9798400706097
The rapid progress of AI-powered programming assistants, such as GitHub Copilot, has facilitated the development of software applications. These assistants rely on large language models (LLMs), which are foundation models (FMs) that support a wide range of tasks related to understanding and generating language. LLMs have demonstrated their ability to express UML model specifications using formal languages like the Object Constraint Language (OCL). However, the context size of the prompt is limited by the number of tokens an LLM can process. This limitation becomes significant as the size of UML class models increases. In this study, we introduce PathOCL, a novel path-based prompt augmentation technique designed to facilitate OCL generation. PathOCL addresses the limitations of LLMs, specifically their token processing limit and the challenges posed by large UML class models. PathOCL is based on the concept of chunking, which selectively augments the prompts with a subset of UML classes relevant to the English specification. Our findings demonstrate that PathOCL, compared to augmenting the complete UML class model (UML-Augmentation), generates a higher number of valid and correct OCL constraints using the GPT-4 model. Moreover, the average prompt size crafted using PathOCL significantly decreases when scaling the size of the UML class models.
The pioneering research on message passing for Java (MPJ) which started after 1995 provided a crucially important framework and programming environment for parallel and distributed computing with Java. This framework ...
详细信息
ISBN:
(纸本)9798350340754
The pioneering research on message passing for Java (MPJ) which started after 1995 provided a crucially important framework and programming environment for parallel and distributed computing with Java. This framework resulted in an industry standard specification and a novel MPJ-based hierarchical development methodology for a new generation of large-scale distributed systems. The invention of a novel component-based model and methodology for rapid distributed software development and execution based on the MPJ work and achievements are the core contributions presented in this paper. Based on the high-performance Java component-based model, concepts and research results, grid, cloud, and extreme-scale computing represent a fundamental shift in the delivery of information technology services that has permanently changed the computing landscape.
Artificial intelligence (AI) assistants such as GitHub Copilot and ChatGPT, built on large language models like GPT-4, are revolutionizing how programming tasks are performed, raising questions about whether code is a...
详细信息
ISBN:
(纸本)9798350363982;9798400705878
Artificial intelligence (AI) assistants such as GitHub Copilot and ChatGPT, built on large language models like GPT-4, are revolutionizing how programming tasks are performed, raising questions about whether code is authored by generative AI models. Such questions are of particular interest to educators, who worry that these tools enable a new form of academic dishonesty, in which students submit AI-generated code as their work. Our research explores the viability of using code stylometry and machine learning to distinguish between GPT-4 generated and human-authored code. Our dataset comprises human-authored solutions from CodeChef and AI-authored solutions generated by GPT-4. Our classifier outperforms baselines, with an F1-score and AUC-ROC score of 0.91. A variant of our classifier that excludes gameable features (e.g., empty lines, whitespace) still performs well with an F1-score and AUC-ROC score of 0.89. We also evaluated our classifier on the difficulty of the programming problem and found that there was almost no difference between easier and intermediate problems, and the classifier performed only slightly worse on harder problems. Our study shows that code stylometry is a promising approach for distinguishing between GPT-4 generated code and human-authored code.
In today’s world industrial robot are widely used in various manufacturing operations. But the main drawback of these robots is the excessive use of material to make them structurally rigid, which in turn increases t...
详细信息
The proceedings contain 27 papers. The special focus in this conference is on Bridging the Gap between AI and Reality. The topics include: Towards a Formal Account on Negative Latency;Track C1: Safety Verifi...
ISBN:
(纸本)9783031460012
The proceedings contain 27 papers. The special focus in this conference is on Bridging the Gap between AI and Reality. The topics include: Towards a Formal Account on Negative Latency;Track C1: Safety Verification of Deep Neural Networks (DNNs);formal Verification of a Neural Network Based Prognostics System for Aircraft Equipment;the Inverse Problem for Neural Networks;continuous engineering for Trustworthy Learning-Enabled Autonomous Systems;benchmarks: Semantic Segmentation Neural Network Verification and Objection Detection Neural Network Verification in Perceptions Tasks of Autonomous Driving;benchmark: Neural Network Malware Classification;benchmark: Remaining Useful Life Predictor for Aircraft Equipment;benchmark: Object Detection for Maritime Search and Rescue;Welcome Remarks from AISoLA 2023/Track C2 Chairs;benchmark: Formal Verification of Semantic Segmentation Neural Networks;empirical Analysis of Benchmark Generation for the Verification of Neural Network Image Classifiers;AI Assisted programming: (AISoLA 2023 Track Introduction);large Language Model Assisted Software engineering: Prospects, Challenges, and a Case study;ChatGPT in the Loop: A Natural Language Extension for Domain-Specific Modeling Languages;what Can Large Language Models Do for Theorem Proving and Formal Methods?;integrating Distributed component-Based Systems Through Deep Reinforcement Learning;Safe AI in Autonomous Vehicles: Track at AISoLA 2023;shielded Reinforcement Learning for Hybrid Systems;what, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety-Critical Systems;deepAbstraction++: Enhancing Test Prioritization Performance via Combined Parameterized Boxes;shielded Learning for Resilience and Performance Based on statistical Model Checking in Simulink;Formal XAI via Syntax-Guided Synthesis;Differential Safety Testing of Deep RL Agents Enabled by Automata Learning;gRoMA: A Tool for Measuring the Global Robustness of Deep Neural Networks.
In recent years, a trend has developed to use Escape Rooms in an educational context. As a consequence, several research has been conducted investigating the integration and design of such Escape Rooms. However, there...
详细信息
ISBN:
(纸本)9783031268755;9783031268762
In recent years, a trend has developed to use Escape Rooms in an educational context. As a consequence, several research has been conducted investigating the integration and design of such Escape Rooms. However, there is a lack of research on concrete implementation from a technical perspective. This paper aims to give detailed insights into a hands-on implementation of an Escape Room architecture that was introduced in a Java programming course at a higher education institution. The proposed architecture consists of multiple loosely coupled components resulting in an extensible and adaptable architecture. This component based approach enables the adaptation of our technical implementation for other domains and educational fields.
Machine learning (ML) has been actively adopted in Linear programming (LP) and Mixed-Integer Linear programming (MILP), whose potential is hindered by instance *** synthetic instance generation methods often fall shor...
详细信息
Machine learning (ML) has been actively adopted in Linear programming (LP) and Mixed-Integer Linear programming (MILP), whose potential is hindered by instance *** synthetic instance generation methods often fall short in closely mirroring the distribution of original datasets or ensuring the feasibility and boundedness of the generated data - a critical requirement for obtaining reliable supervised labels in model *** this paper, we present a diffusion-based LP/MILP instance generative framework called *** strikes a balance between structural similarity and novelty while maintaining feasibility/boundedness via a meticulously designed structure-preserving generation module and a feasibility/boundedness-constrained sampling *** method shows superiority on two fronts: 1) preservation of key properties (hardness, feasibility, and boundedness) of LP/MILP instances, and 2) enhanced performance on downstream *** studies show two-fold superiority that our method ensures higher distributional similarity and 100% feasibility in both easy and hard datasets, surpassing current state-of-the-art techniques. Copyright 2024 by the author(s)
In the modern and digital society, the importance of software development is undeniable. Therefore, educating the next generation of software developers is crucial. However, learning how to program is challenging, and...
详细信息
ISBN:
(纸本)9783031056574;9783031056567
In the modern and digital society, the importance of software development is undeniable. Therefore, educating the next generation of software developers is crucial. However, learning how to program is challenging, and research on improving programming pedagogy is essential. Adding a laboratory component to programming courses can enhance the education. In this work, we first elicited requirements and guidelines for an introductory programming lab curriculum based on a literature review and feedback by instructors with years of experience. These included the use of (1) current and adequate tools, (2) collaborative learning environment, (3) formative assessment, (4) appropriate assignments for the target audience, (5) pedagogical innovations, and (6) to prepare students to be lifelong learners of the subject. Following, we present a curriculum for an introductory undergraduate programming lab based on the Raspberry Pi platform. It teaches students how to program following software development best practices and integrate software and hardware through a series of cyber-physical assignments, including developing a rover vehicle. We successfully piloted the curriculum with 30 students, and we present the highly positive feedback provided by them. Although the course was based on the C programming language, the underlying foundation on programming principles will allow students to apply the concepts in any language. Furthermore, this curriculum is not intended to be a one-size-fits-all approach to programming education. However, it can be a strong starting point for readers to tailor it to fit their audience, school needs, and student learning outcomes.
This paper describes the procedure for designing a modified adaptive-relay control using the Recursive Least Square and pole placement algorithm intended to control the output voltage of the Two Level Boost Converter....
详细信息
暂无评论