检索结果-内蒙古大学图书馆

automated programming, symbolic computation, machine learning: my personal view

ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE 2023年第5期91卷 569-589页

作者： Buchberger, Bruno Johannes Kepler Univ Linz Res Inst Symbol Computat RISC Linz Austria

In this note, I present my personal view on the interaction of the three areas automated programming, Symbolic Computation, and Machine Learning. programming is the activity of finding a (hopefully) correct program (algorithm) for a given problem. programming is central to automation in all areas and is considered one of the most creative human activities. However, already very early in the history of programming, people started to "jump to the meta-level" of programming, i.e., started to develop procedures that automate, or semi-automate, (various aspects or parts of) the process of programming. This area has various names like "automated programming", "automated Algorithm Synthesis", etc. Developing compilers can be considered an early example of a problem in automated programming. automated reasoners for proving the correctness of programs with respect to a specification is an advanced example of a topic in automated programming. ChatGPT producing (amazingly good) programs from problem specifications in natural language is a recent example of automated programming. programming tends to become the most important activity as the level of technological sophistication increases. Therefore, automating programming is maybe the most exciting and relevant technological endeavor today. It also will have enormous impact on the global job market in the software industry. Roughly, I see two main approaches to automated programming:symbolic computationand machine learning. In this note, I explain how the two approaches work and that they are fundamentally different because they address two completely different ways of how problems are specified. Together, the two approaches constitute (part of) what some people like to call "artificial intelligence". In my analysis, both approaches are just part of (algorithmic) mathematics. The approaches, like all non-trivial mathematical methods, need quite some intelligence on the side of the human inventors of the methods. However, apply

关键词： automated programming Symbolic computation automated reasoning Machine learning Artificial intelligence Artificial general intelligence Pretrained large language models Software industry programming assistant. .

来源：评论

学校读者我要写书评

暂无评论

A ChatGPT-MATLAB framework for numerical modeling in geotechnical engineering applications

引用

COMPUTERS AND GEOTECHNICS 2024年 169卷

作者： Kim, Daehyun Kim, Taegu Kim, Yejin Byun, Yong-Hoon Yun, Tae Sup Yonsei Univ Dept Civil & Environm Engn Yonsei Ro 50 Seoul 03722 South Korea Hiroshima Univ Dept Civil & Environm Engn 1-4-1 Kagamiyama Higashihiroshima Hiroshima 7398527 Japan Kyungpook Natl Univ Sch Agr Civil & Bioind Engn 80 Daehak Ro Daegu 41566 South Korea

ChatGPT has recently emerged as a representative of Large Language Models (LLMs) that have brought evolutionary changes to our society, and the effectiveness of ChatGPT in various applications has been increasingly reported. This study aimed to explore the potential of employing programming performance driven by ChatGPT responses to conversational prompts in the field of geotechnical engineering. The tested examples included the analysis of seepage flow and slope stability, and the image processing of X-ray computed tomographic image for partially saturated sand. For each case, the prompt was initially fed by a narrative explanation of the problem attributes such as geometry, initial conditions, and boundary conditions to generate the MATLAB code that was in turn executed to evaluate the correctness and functionality. Any errors and unanticipated results were further refined by additional prompts until the correct outcome was achieved. ChatGPT was able to generate the numerical code at a considerable level, demonstrating creditable awareness of the refining process, when meticulous prompts were provided based on a comprehensive understanding of given problems. While ChatGPT may not be able to replace the entire process of programming, it can help minimize sloppy syntax errors and assist in designing a basic framework for logical programming.

关键词： ChatGPT Numerical modeling automated programming Artificial Intelligence (AI) Large Language Model (LLM)

来源：评论

学校读者我要写书评

暂无评论

Closed-loop programming using external responses for deep brain stimulation in Parkinson's disease

引用

PARKINSONISM & RELATED DISORDERS 2021年 84卷 47-51页

作者： Sasaki, Fuyuko Oyama, Genko Sekimoto, Satoko Nuermaimaiti, Maierdanjiang Iwamuro, Hirokazu Shimo, Yasushi Umemura, Atsushi Hattori, Nobutaka Juntendo Univ Dept Neurol Sch Med Tokyo Japan Juntendo Univ Dept Res & Therapeut Movement Disorders Grad Sch Med Tokyo Japan Juntendo Univ Dept Neurosurg Sch Med Tokyo Japan Juntendo Univ Dept Neurol Nerima Hosp Tokyo Japan

Introduction: Deep brain stimulation (DBS) is an established treatment for Parkinson's disease (PD). Clinicians face various challenges in adjusting stimulation parameters and configurations in clinical DBS settings owing to inexperience, time constraints, and recent advances in DBS technology that have expanded the number of possible contact configurations. We aimed to assess the efficacy of a closed-loop algorithm (CLA) for the DBS-programming method using external motion sensor-based motor assessments in patients with PD. Methods: In this randomized, double-blind, crossover study, we enrolled 12 patients who underwent eight-ring-contact DBS lead implantations bilaterally in the subthalamic nucleus. The DBS settings of the participants were programmed using a standard of care (SOC) and CLA method. The clinical effects of both programming methods were assessed in a randomized crossover fashion. The outcomes were evaluated using the Unified Parkinson's Disease Scale part III (UPDRS-III) and sensor-based scores for baseline (medication-off/stimulation-off) and both programming methods. The number of programming steps required for each programming method was also recorded. Results: The UPDRS-III scores and sensor-based scores were significantly improved by SOC and CLA settings compared to the baseline. No statistical difference was observed between SOC and CLA. The programming steps were significantly reduced in the CLA settings compared to those in the SOC. No serious adverse events were observed. Conclusion: CLA can optimize DBS settings prospectively with similar therapeutic benefits as that of the SOC and reduce the number of programming steps. automated optimization of DBS settings would reduce the burden of programming for both clinicians and patients.

关键词： Parkinson's disease Deep brain stimulation Closed loop programming automated programming Wearable sensor Objective assessment

来源：评论

学校读者我要写书评

暂无评论

Derivations with Holes for Concept-Based Program Synthesis

Derivations with Holes for Concept-Based Program Synthesis

引用

ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on programming and Software (Onward!)

作者： Seco, Joao Costa Aldrich, Jonathan Carvalho, Luis Toninho, Bernardo Ferreira, Carla NOVA Univ Lisbon NOVA LINCS Caparica Portugal Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781450399098

Program synthesis has the potential to democratize programming by enabling non-programmers to write software. But conventional approaches to synthesis may fail if given insufficient information-a common occurrence when asking non-experts to describe the application they want to write. This paper introduces a new concept-based program synthesis mechanism that can cope with incomplete knowledge, targeting low-code model-driven languages. Concepts are modelled in an ontology that represents user intent, including basic actions (e.g. show, filter, and create) along with their associated data as well as basic user interface structures like screens or pages. Our synthesis framework consists of a system of derivation rules that supports deferred premises, which need not be immediately satisfied during synthesis. A derivation in which some deferred premises are missing will thus contain holes;semantically, it represents a proof that is conditional on the developer filling the holes with additional facts from the ontology. We translate derivations with holes to standard first-order logic derivations, where the holes are transformed into assumptions. We illustrate the feasibility and effectiveness of our framework with a proof-of-concept implementation and a set of illustrative examples.

关键词： low-code program synthesis automated programming user intent incomplete knowledge

来源：评论

学校读者我要写书评

暂无评论

Exploration of the Insider Threat Using Semi-Automatic Bug Generation

Exploration of the Insider Threat Using Semi-Automatic Bug G...

引用

作者： Westland, Tyler University of Cincinnati

学位级别：Ph.D., Doctor of Philosophy

The work shown in this thesis explores a rogue developer desiring to make a small bug in the system they are working on. This insider threat's main focus is thus the semi-automatic generation of a bug. This is achieved using patch generation, a type of automated programming, which is normally used to fix bugs. We do so first on small single file programs, and then expand to an open source project. Within the open source project we refine our search of the search space Furthermore we explored injecting bugs with a specified trigger that are not caught by the test suite for the open source project.

关键词： Insider threat Semi-automatic bug generation Patch generation automated programming

来源：评论

学校读者我要写书评

暂无评论

Nonlinear shape optimization of flexible mechanical metamaterials

引用

EXTREME MECHANICS LETTERS 2023年 61卷

作者： Medina, Eder Rycroft, Chris H. Bertoldi, Katia Harvard Univ Harvard John A Paulson Sch Engn & Appl Sci Cambridge MA 02138 USA Univ Wisconsin Dept Math Madison WI 53706 USA Lawrence Berkeley Lab Computat Res Div Berkeley CA 94720 USA

Shape optimization is used to design flexible mechanical metamaterials. We employ the higher-order moving-mesh method to arbitrarily parameterize the geometries and tune their nonlinear mechanical response to our liking under different loading conditions. Rather than considering periodic unit cells, we focus on finite size elastomeric sheets with an embedded array of pores subjected to uniaxial tension, compression, and shear and use the optimization algorithm to tune either their stress-strain response or their effective Poisson's ratio. We find that for all considered targets the algorithm converges to aperiodic geometries that are non-intuitive and comprise domain-like features. As such, our results indicate that aperiodicity may provide new opportunities for the design of flexible metamaterials.& COPY;2023 Elsevier Ltd. All rights reserved.

关键词： Shape optimization Flexible structures automated programming Optimization

来源：评论

学校读者我要写书评

暂无评论

On Multi-Modal Learning of Editing Source Code 36

On Multi-Modal Learning of Editing Source Code

引用

36th IEEE/ACM International Conference on automated Software Engineering (ASE)

作者： Chakraborty, Saikat Ray, Baishakhi Columbia Univ Dept Comp Sci New York NY 10027 USA

ISBN: (纸本)9781665403375

In recent years, Neural Machine Translator (NMT) has shown promise in automatically editing source code. Typical NMT based code editor only considers the code that needs to be changed as input and suggests developers with a ranked list of patched code to choose from - where the correct one may not always be at the top of the list. While NMT based code editing systems generate a broad spectrum of plausible patches, the correct one depends on the developers' requirement and often on the context where the patch is applied. Thus, if developers provide some hints, using natural language, or providing patch context, NMT models can benefit from them. As a proof of concept, in this research, we leverage three modalities of information: edit location, edit code context, commit messages (as a proxy of developers' hint in natural language) to automatically generate edits with NMT models. To that end, we build MODIT, a multi-modal NMT based code editing engine. With in-depth investigation and analysis, we show that developers' hint as an input modality can narrow the search space for patches and outperform state-of-the-art models to generate correctly patched code in top-1 position.

关键词： Source Code Edit Neural Networks automated programming Neural Machine Translator Pretraining Transformers

来源：评论

学校读者我要写书评

暂无评论

CloudifierNet - Deep Vision Models for Artificial Image Processing 7

CloudifierNet - Deep Vision Models for Artificial Image Proc...

引用

7th International Conference on Information Technology and Quantitative Management (ITQM) - Information Technology and Quantitative Management Based on Artificial Intelligence

作者： Damian, Andrei Ionut Piciu, Laurentiu Purdila, Alexandru Tapus, Nicolae Lummetry AI Bucharest Romania Univ Politehn Bucuresti Bucharest Romania

Today, more and more, it is necessary that most applications and documents developed in previous or current technologies to be accessible online on cloud-based infrastructures. That's why the migration of legacy systems including their hosts of documents to new technologies and online infrastructures, using modem Artificial Intelligence techniques, is absolutely necessary. With the advancement of Artificial Intelligence and Deep Learning with its multitude of applications, a new area of research is emerging that of automated systems development and maintenance. The underlying work objective that led to this paper aims to research and develop truly intelligent systems able to analyze user interfaces from various sources and generate real and usable inferences ranging from architecture analysis to actual code generation. One key element of such systems is that of artificial scene detection and analysis based on deep learning computer vision systems. Computer vision models and particularly deep directed acyclic graphs based on convolutional modules are generally constructed and trained based on natural images datasets. Due to this fact, the models will develop during the training process natural image feature detectors apart from the base graph modules that will learn basic primitive features. In the current paper, we will present the base principles of a deep neural pipeline for computer vision applied to artificial scenes (scenes generated by user interfaces or similar). Finally, we will present the conclusions based on experimental development and benchmarking against state-of-the-art transfer-learning implemented deep vision models. (C) 2020 The Authors. Published by Elsevier B.V.

关键词： artificial intelligence deep learning computer vision automated programming collaborative work

来源：评论

学校读者我要写书评

暂无评论

CloudifierNet - Deep Vision Models for Artificial Image Processing

引用

Procedia Computer Science 2019年 162卷 720-728页

作者： Andrei Ionut Damian Laurentiu Piciu Alexandru Purdila Nicolae Tapus Lummetry.AI Bucharest Romania University “Politehnica” Bucharest Romania

Today, more and more, it is necessary that most applications and documents developed in previous or current technologies to be accessible online on cloud-based infrastructures. That’s why the migration of legacy systems including their hosts of documents to new technologies and online infrastructures, using modern Artificial Intelligence techniques, is absolutely necessary. With the advancement of Artificial Intelligence and Deep Learning with its multitude of applications, a new area of research is emerging – that of automated systems development and maintenance. The underlying work objective that led to this paper aims to research and develop truly intelligent systems able to analyze user interfaces from various sources and generate real and usable inferences ranging from architecture analysis to actual code generation. One key element of such systems is that of artificial scene detection and analysis based on deep learning computer vision systems. Computer vision models and particularly deep directed acyclic graphs based on convolutional modules are generally constructed and trained based on natural images datasets. Due to this fact, the models will develop during the training process natural image feature detectors apart from the base graph modules that will learn basic primitive features. In the current paper, we will present the base principles of a deep neural pipeline for computer vision applied to artificial scenes (scenes generated by user interfaces or similar). Finally, we will present the conclusions based on experimental development and benchmarking against state-of-the-art transfer-learning implemented deep vision models.

关键词： artificial intelligence deep learning computer vision automated programming collaborative work

来源：评论

学校读者我要写书评

暂无评论

Modeling and control of flexible context-dependent manufacturing systems

引用

INFORMATION SCIENCES 2017年 421卷 1-14页

作者： Silva, Andre Lucas Ribeiro, Richardson Teixeira, Marcelo Univ Tecnol Fed Parana Pato Branco Brazil

In emerging Manufacturing Systems (MSs), flexibility is a key issue. It is related to the ability for a MS to recognize the context and switch its workflow accordingly. Although the literature has provided automated options to model and control MSs, programming context-dependent controllers remains challenging. This is an event-based construction that integrates a large and intricate combination of events and states in order to make the controller flexible, i.e., include context-sensitiveness strategies subject to switching at runtime. Without self-adaptation, each system configuration may require an entire control solution to be recalculated, which implies redesigning the whole modeling and implementation structures. This paper shows that a system model can nevertheless be enriched with elements collected from the context, which optimizes the design of formula-based constraints that can then be integrated to control frameworks for synthesis and code generation. The result is a controller that recognizes the context and takes control decisions accordingly. Examples are provided to illustrate the approach. (C) 2017 Elsevier Inc. All rights reserved.

关键词： Formal modeling Context recognition automated programming Factory automation Flexible manufacturing systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：