Architecture and Knowledge Representation for Composable Inductive Programming

• URL: http://arxiv.org/abs/2212.12320v1
• Date: Thu, 22 Dec 2022 17:02:19 GMT
• Title: Architecture and Knowledge Representation for Composable Inductive Programming
• Authors: Edward McDaid, Sarah McDaid
• Abstract summary: We present an update on the current architecture of the Zoea knowledge-based, Composable Inductive Programming system. The Zoea compiler is built using a modern variant of the black-board architecture.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present an update on the current architecture of the Zoea knowledge-based, Composable Inductive Programming system. The Zoea compiler is built using a modern variant of the black-board architecture. Zoea integrates a large number of knowledge sources that encode different aspects of programming language and software development expertise. We describe the use of synthetic test cases as a ubiquitous form of knowledge and hypothesis representation that sup-ports a variety of reasoning strategies. Some future plans are also outlined.

Related papers

• Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Maintenance [9.603528792596348]
  We introduce the concept and framework of textbfCode Digital Twin, a conceptual representation of tacit knowledge. A code digital twin is constructed using a methodology that combines knowledge extraction from both structured and unstructured sources.
  arXiv  Detail & Related papers  (2025-03-11T01:46:58Z)
• Revisiting Abstractions for Software Architecture and Tools to Support Them [0.9558392439655016]
  We present a conceptual view of software architecture based on abstractions used in practice to organize software systems. We reflect on the paper's principal ideas about system-level abstractions. We describe current manifestations of architectural ideas and current challenges.
  arXiv  Detail & Related papers  (2025-03-06T01:48:25Z)
• A Symbolic Computing Perspective on Software Systems [0.0]
  Symbolic mathematical computing systems have served as a canary in the coal mine of software systems for more than sixty years. All of the major symbolic mathematical computing systems include low-level code for arithmetic, memory management and other primitives, a compiler or interpreter for a bespoke programming language, a library of high level mathematical algorithms, and some form of user interface.
  arXiv  Detail & Related papers  (2024-06-13T13:10:47Z)
• Finding structure in logographic writing with library learning [55.63800121311418]
  We develop a computational framework for discovering structure in a writing system. Our framework discovers known linguistic structures in the Chinese writing system. We demonstrate how a library learning approach may help reveal the fundamental computational principles that underlie the creation of structures in human cognition.
  arXiv  Detail & Related papers  (2024-05-11T04:23:53Z)
• Standardizing Knowledge Engineering Practices with a Reference Architecture [8.22187358555391]
  This paper proposes a vision of harmonizing the best practices in the field of knowledge engineering. We describe how a reference architecture can be iteratively designed and implemented to associate user needs with recurring systemic patterns.
  arXiv  Detail & Related papers  (2024-04-04T17:46:32Z)
• Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit [63.82016263181941]
  Code intelligence leverages machine learning techniques to extract knowledge from extensive code corpora. Currently, there is already a thriving research community focusing on code intelligence.
  arXiv  Detail & Related papers  (2023-12-30T17:48:37Z)
• UNTER: A Unified Knowledge Interface for Enhancing Pre-trained Language Models [100.4659557650775]
  We propose a UNified knowledge inTERface, UNTER, to provide a unified perspective to exploit both structured knowledge and unstructured knowledge. With both forms of knowledge injected, UNTER gains continuous improvements on a series of knowledge-driven NLP tasks.
  arXiv  Detail & Related papers  (2023-05-02T17:33:28Z)
• WikiCoder: Learning to Write Knowledge-Powered Code [0.0]
  This paper makes a first step towards knowledge-powered program synthesis. We present WikiCoder, a system building upon state of the art machine-learned program synthesizers and integrating knowledge graphs.
  arXiv  Detail & Related papers  (2023-03-15T12:50:54Z)
• A Compositional Approach to Creating Architecture Frameworks with an Application to Distributed AI Systems [16.690434072032176]
  We show how compositional thinking can provide rules for the creation and management of architectural frameworks for complex systems. The aim of the paper is not to provide viewpoints or architecture models specific to AI systems, but instead to provide guidelines on how a consistent framework can be built up with existing, or newly created, viewpoints.
  arXiv  Detail & Related papers  (2022-12-27T18:05:02Z)
• MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning [50.40151403246205]
  Huge language models (LMs) have ushered in a new era for AI, serving as a gateway to natural-language-based knowledge tasks. We define a flexible architecture with multiple neural models, complemented by discrete knowledge and reasoning modules. We describe this neuro-symbolic architecture, dubbed the Modular Reasoning, Knowledge and Language (MRKL) system.
  arXiv  Detail & Related papers  (2022-05-01T11:01:28Z)
• Leveraging Language to Learn Program Abstractions and Search Heuristics [66.28391181268645]
  We introduce LAPS (Language for Abstraction and Program Search), a technique for using natural language annotations to guide joint learning of libraries and neurally-guided search models for synthesis. When integrated into a state-of-the-art library learning system (DreamCoder), LAPS produces higher-quality libraries and improves search efficiency and generalization.
  arXiv  Detail & Related papers  (2021-06-18T15:08:47Z)
• DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning [47.910312960048174]
  We present DreamCoder, a system that learns to solve problems by writing programs. It builds expertise by creating programming languages for expressing domain concepts, together with neural networks. A wake-sleep'' learning algorithm alternately extends the language with new symbolic abstractions and trains the neural network on imagined and replayed problems.
  arXiv  Detail & Related papers  (2020-06-15T13:06:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.