关于机器学习和人工神经网络
卓晴 TsinghuaJoking
在昨天人工神经网络课程之后,有一位同学课下问了一个问题,她这学期也在学习“机器学习”课程,感觉“人工神经网络”课程的内容与机器学习课程的内容大同小异。究竟这些课程之间有何区别呢?弄不清楚这些自己这学期的课程很是担心。
之所以产生这样的疑问,原因来自于这两门课程之间的相似之处,而且随着学科的发展它们重合度也在增加。但它们之间的差异在哪儿呢?
除了它们各自发展的理论和技术历史和路径不同、未来研究热点和实现途径差异之外,也许认清它们之间的联系更重要。
DJ Patil在他的一个短片中 What’s the difference between ML and NN? 总结了机器学习和人工神经网络几点关系:
▲ DJ Patil: What's the difference between ML and NN?
-
一种对人工神经网络,机器学习,人工智能之间关系的最基本看法是:人工神经网络是众多问题解决方案中的一种;
- 现今阶段你所能看到的人工神经网络大部分是一种使用大量数据训练的多层深度学习网络,并在传统的误差反向传播(BP)技术之上衍生出很多其他特性;
- 对于神经网络算法的提高也使得它与机器学习方法有了很多共同之处:比如监督学习、非监督学习、Logistic回归、随机森林等。这些方法的共同之处都是通过一些训练数据及来寻找到一些满足某些约束条件的函数映射。
近日,一篇来自于斯坦福大学的人工智能定义短文 Artificial Intelligence Definitions 从某一角度较为详细的把智能相关的概念进行了梳理,阅读它也许可以帮你尽可能理清这个领域中的众多学科之间的关系。
智能 可以被定义为在不确定、时刻变化的环境中通过学习和实施合适的技术来解决碰到的问题或达到既定目标的能力。而那种安全靠编程来灵活、精确、可靠工作的工厂中的机器人则不具有智能。
Intelligence might be defined as the ability to learn and perform suitable techniques to solve problems and achieve goals, appropriate to the context in an uncertain,ever-varying world. A fully pre-programmed factory robotis flexible, accurate, and consistent but not intelligent.
人工智能 这一词语是由斯坦福大学退休名誉教授 McCarthy 在1955年提出,是指:“制造出智能设备的科学和工程技术。” 多数研究是通过计算机编程使得机器表现出聪明,比如下象棋。但今天我们更强调机器能够像人类一样进行学习。
Artificial Intelligence (AI), a term coined by emeritus Stanford Professor John McCarthy in 1955,was defined by him as “the science and engineering of making intelligent machines”. Much research has humans program machines to behave in a clever way, like playing chess, but, today, we emphasize machines that can learn,at least somewhat like human beings do.
自主系统 无需借助底层(微小)管理便可以自主对完成特定目标的步骤进行规划和决策。比如在医院里递送药品的机器人可以成功穿越拥挤的走廊完成这个任务。在人工智能中的自主,与政治和生物领域中的自主概念并不相同。
Autonomous systems can independently plan and decide sequences of steps to achieve a specified goal without micro-management. A hospital delivery robot must autonomously navigate busy corridors to succeed in its task. In AI, autonomy doesn’t have the sense of being self-governing common in politics or biology.
机器学习 是人工智能中研究如何通过计算机软件,在已有的经验和数据的基础上提高感知、知识、思考和行动能力。为实现这个目的,机器学习应用了计算机科学、统计学、心理学、神经科学、经济学(?) 以及控制理论。
Machine Learning (ML) is the part of AI studying how computer agents can improve their perception,knowledge, thinking, or actions based on experience or data. For this, ML draws from computer science, statistics,psychology, neuroscience, economics and control theory.
监督学习 计算机软件从人类给定数据的标签中来进行预测,比如从狗的图片来预测狗的品种。 无监督学习 则无需数据标签,有时是自行完成预测任务,例如预测一个句子中词语的前后顺序。 增强学习 是根据总的奖赏条件来自行确定要执行任务,比如在游戏中,无需给定哪种好的技术,它便可以自行学习。
In supervised learning, a computer learns to predict human-given labels, such as dog breed based on labeled dog pictures; unsupervised learning doesnot require labels, sometimes making its own prediction tasks such as trying to predict each successive word in a sentence; reinforcement learning lets an agent learn action sequences that optimize its total rewards,such as winning games, without explicit examples of good techniques, enabling autonomy.
深度学习 则通过使用大型多层人工神经网络 形成类似于人脑中神经元的层次结构,计算它们之间连续变化的权值。这是当今机器学习各种方法中应用最为成功的方法。无论数据集合大小还是计算能力消耗量,它都能够很好的推广。
Deep Learning is the use of large multi-layer(artificial) neural networks that compute with continuous (real number) representations, a little like the hierarchically organized neurons in human brains. It is currently the most successful ML approach, usable for all types of ML, with better generalization from small data and better scaling to big data and compute budgets.
普通的算法需要像编写的计算机程序那样有精确的执行步骤。而人工智能算法则只有少量的用于描述学习和奖励的计算方法,大部分算法的性能则是通过对数据和经验的学习来获得。对于这种巨大的变化,b毕业于斯坦福大学的Andrej Kapathy称为它 软件的2.0版本。
An algorithm lists the precise steps to take, such as a person writes in a computer program. AI systems contain algorithms, but often just for a few parts like a learning or reward calculation method. Much of their behavior emerges via learning from data or experience,a sea change in system design that Stanford alumnus Andrej Karpathy dubbed Software 2.0.
狭义的人工智能 是为了完成特定任务,比如语音、人脸识别。类人智能,或者广义智能 则是探索更加一般性的智能,适用不同语境的机器。比如一些社交聊天机器人或者人与机器人的交互等。
Narrow AI is intelligent systems for one particular thing, e.g., speech or facial recognition.Human-level AI, or Artificial General Intelligence (AGI), seeks broadly intelligent,context-aware machines. It is needed for effective social chatbots or human-robot interaction.
聚焦人类人工智能 则是为增加人的能力、解决社会需求、从人类行为获得启发的人工智能,研究制作人类更加有效伙伴和工具,比如对老年人的辅助和关爱机器人。
Human-Centered Artificial Intelligence is AI that seeks to augment the abilities of, address the societal needs of, and draw inspiration from human beings. It researches and builds effective partners and tools for people, such as a robot helper and companion for the elderly.