Machine Learning definition
- Arthur Samuel(1959). Machine Learing :Field of study that gives computers the ability to learn without being explicitly programmed.
在进行特定编程的情况下赋予计算机学习能力的领域
- Tom Mitchell (1998)Well-posed Learning Problem:A computer program is said to learn from experience E with respect to some task T and some performance measure P， if its performance on T, as measured by P, improves with experience E.
一个程序被认为能从经验中学习，解决任务T，达到性能度量值P，当且仅当有了经验E后，经过P评判，程序在处理T时的性能有所提升。
Machine learing algorithms:
- Supervised learning
- Unsupervised learning
- Others:Reinforcement learning, recommender systems.
Also talk about:Practical advice for applying learning algorithms. - 监督学习
- 非监督学习
- 其他：强化学习，推荐系统
接下来的主要任务是：了解应用学习算法的实用建议。
Examples:
- Database mining
Large datasets from growth of automation/web.
E.g., Web click data, medical records, biology, eng
ineering - Applications can’t program by hand.
E.g., Autonomous helicopter, handwriting recognitio
n, most of
Natural Language Processing (NLP), Computer Vision. - Self-customizing programs
E.g., Amazon, Netflix product recommendations - Understanding human learning (brain, real AI).
以上摘自 Andrew Ng。
第一节课了解到机器学习的定义，课程主要是讲算法的选择与应用。其中老师提到接下来的时间将会花费大量时间
在机器学习、人工智能的最佳实践以及如何让他们工作上，我们该如何去做，也就是学习并学会使用这些算法。
