arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1409.8027cs.AI
收藏

自主机器人和智能的SP理论

Autonomous robots and the SP theory of intelligence

J. Gerard Wolff

摘要:

这篇文章是关于“智能的SP理论”及其在“SP机”中的实现(都在文章中概述)如何帮助解决自主机器人设计中与计算机相关的问题,这意味着机器人不依赖于外部智能或电源,是移动的,并且被设计为尽可能多地表现出类似人类的智能。这篇文章是关于:如何提高计算机的计算效率和能源效率,并减少其体积;如何实现智能中的人类通用性;以及智能中的人类适应性。SP系统有可能在计算和能源效率方面取得实质性进展,并减少计算机的体积:通过减少要处理的数据的大小;通过利用系统收集的统计信息;并通过更新版本的Donald Hebb的“细胞组装”概念。SP系统在无监督学习、自然语言处理、模式识别、信息检索、多种推理、规划、问题解决等方面具有与人类相似的智能多功能性,并且在结构和功能之间具有无缝集成。SP系统在无监督学习和其他智能方面的优势可能有助于通过以下方式实现类似人类的智能适应性:学习自然语言;学习看;构建物体和机器人周围环境的3D模型;学习机器人工作和机器人环境中的知识;探索和玩耍;学习主要技能;以及次要形式的学习。还讨论了:SP系统如何处理并行信息流;知识的概括,纠正过度概括,从脏数据中学习;如何降低学习成本;强化,动机,目标和演示。

英文摘要:

This article is about how the "SP theory of intelligence" and its realisation in the "SP machine" (both outlined in the article) may help to solve computer-related problems in the design of autonomous robots, meaning robots that do not depend on external intelligence or power supplies, are mobile, and are designed to exhibit as much human-like intelligence as possible. The article is about: how to increase the computational and energy efficiency of computers and reduce their bulk; how to achieve human-like versatility in intelligence; and likewise for human-like adaptability in intelligence. The SP system has potential for substantial gains in computational and energy efficiency and reductions in the bulkiness of computers: by reducing the size of data to be processed; by exploiting statistical information that the system gathers; and via an updated version of Donald Hebb's concept of a "cell assembly". Towards human-like versatility in intelligence, the SP system has strengths in unsupervised learning, natural language processing, pattern recognition, information retrieval, several kinds of reasoning, planning, problem solving, and more, with seamless integration amongst structures and functions. The SP system's strengths in unsupervised learning and other aspects of intelligence may help to achieve human-like adaptability in intelligence via: the learning of natural language; learning to see; building 3D models of objects and of a robot's surroundings; learning regularities in the workings of a robot and in the robot's environment; exploration and play; learning major skills; and secondary forms of learning. Also discussed are: how the SP system may process parallel streams of information; generalisation of knowledge, correction of over-generalisations, and learning from dirty data; how to cut the cost of learning; and reinforcements, motivations, goals, and demonstration.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑