论文部分内容阅读
学习能力是人类智能的根本特征.2016年3月,Google公司的Alpha Go把深度神经网络与蒙特卡罗树形搜索结合起来,以4胜1负的成绩战胜了围棋世界冠军韩国的李世石.这一结果标志人工智能取得了重大进展.本文重点介绍Alpha Go采用的机器学习方法,包括强化学习、深度学习、深度强化学习,分析存在的问题和最新的研究进展.为了突破通过计算机进行学习的极限,提出认知机器学习,列举可能的研究方向开展研究,使机器智能不断进化,逐步达到人类水平.
Learning ability is a fundamental feature of human intelligence, and in March 2016, Google’s Alpha Go combined Deep Neural Networks with Monte Carlo tree search to defeat Lee Goh Seok, South Korea’s Go champion, in a 4-1 record. As a result, significant progress has been made in artificial intelligence.This article focuses on the machine learning methods used by Alpha Go, including intensive learning, deep learning, intensive learning, the analysis of existing problems and the latest research progress.In order to break through the limit of learning by computer , Put forward cognitive machine learning, enumerating the possible research directions to carry out research, making the machine intelligence evolve gradually and gradually reach the human level.