deeplearning.ai课程笔记（1）

 Andrew Ng: http://www.andrewng.org/
 Geoffrey Hinton: http://www.cs.toronto.edu/~hinton/
 Yann LeCun: http://yann.lecun.com/
 Yoshua Bengio:
 http://www.iro.umontreal.ca/~bengioy/yoshua_en/index.html

       看到这几个深度学习领域领军人物的名字出现在一起，还是在暑期课程自然语言处理课堂上，上图中四个人的合照，内心触动无比！ 膜拜和激动之情不亚于当初看到物理学界的那张珍贵合照！就是这些牛人们，用知识，用想法改变了世界！

       听说了牛人的名字，激动过后，不禁去想，他们各自做的是什么，有哪些贡献，我却说不上来，翻看了自己从接触这个领域以来看过的寥寥无几的论文，四位大牛中，只拜读过Yann LeCunn 的一篇《Gradient-based Learning Applied to Document》,更惭愧的是，现在也无法将内容简要概述出来，模型更没有理解到位。遂将大牛们的主页附上，以求常看和激励。

       合照上Andrew Ng老师还在百度任职，而于今年3月份离职百度后，在6月份首度公布去向，带着新的项目Deeplearning.ai回归.而于前不久，首度公布deeplearning.ai课程正式登录Cousera。这个旨在是向全世界普及深度学习知识的课程，当然让我这只小白欣喜万分，不多说了，开启膜拜旅程，走进这个据说学完后可以创造amazing things的科技！

       内容概述：
       specialization
       first course (four weeks) : the foundations of neural networks;
be able to build a deep neural network to recognize
       second course (three weeks):the practical aspects of deep learning;
hyperparameter tuning, regularization, how to diagnose price and variants and advance aptimization algorithms.black magic.
       third course (two weeks):how to structure your machine learning project
       forth course CNNs, how to build these models
       five course sequence models(RNN、LSTM） apply them to natural language processing and other problems

        附上B站课程观看网址（目前只更新完first course）：
https://www.bilibili.com/video/av13285069/from=search&seid=9684078121307709262#page=1
       感激视频提供者！

---

 附上课程内容文字原稿，本小次PPT精要为上述两页。

1-1-1、Introduction to Deep Learning
    Welcome

    Hello and welcome. As you probably know, deep learning has already transformed traditional internet businesses like web search and advertising. But deep learning is also enabling brand new products and business and ways of helping people to be created. Everything ranging from better healthcare, where deep learning is getting really good at reading X-ray images to delivering personalized education, to precision agriculture, to even self driving cars and many others.
    If you want to learn the tools of deep learning and be able to apply them to build these amazing things, I want to help you get there. When you finish the sequence of courses on Coursera, called the specialization, you will be able to put deep learning ont your resume(履历) with confidence.
    Over the next decade(十年）, I think all of us have an opportunity to build an amazing world, amazing society, that is AI powers, and I hope that you will play a big role in the creation of this AI power scoiety. So that, let’s get started.
    I think that AI is the new electricity. Starting about 100 years ago, the electrification of our scoiety transformed every major industry, every ranging from transportation, manufacturing, to helthcare, to communications and many more.
     And today, we see a surprisingly clear path for AI to bring about an equally big transformation.
    And of course, the part of AI that is rising rapidly and driving a lot of these developments, is deep learning. So today, deep learning is one of the most highly sought after skills and technology worlds.
    And through this course and a few courses after this one, I want to help you to gain and master those skills. So here’s what you learn in this sequence of courses also called a specialization on Coursera.
     In the first course, you learn about the foundations of neural networks, you learn about neural networks and deep learning. This video that you’re watching is part of this first course which last four weeks in total. And each of the five courses in the specialization will be about two to four weeks, with most of them actually shorter than four weeks.
    But in this course，you’ll learn how to build a new network including a deep neural network and how to train it on data. And at the end of this course, you’ll be able to build a deep neural network to recognize, guess what? Cats, for some reason, there is a cat Neem runing around in deep learning. And so, following tradtion in this first course, we’ll build a cat recognizer.   Then in the second course, you learn about the practical aspects of deep learning. So you learn, now that you’ve built in your network, how to actually get it to perform well. So you learn about hyperparameter(超参数） tuning, regularization, how to diagnose price and variants and advance aptimization algorithms like momentum armrest pro（动量什么？？？#待查#）） and the ad authorization algorithm（广告授权算法？#待查#）. Sometimes it seems like there’s a lot of tuning, even some black magic(#待查#） and how you build a new network. So the second course which is just three weeks, will demystify（阐明） some of that black magic.
    In the third course which is just two weeks, you learn how to structure your machine learning project. It turns out that the strategy for building a machine learning system has changed in the era of deep learning. So for example, the way you switch your data into train, development or dev also called holdout cross-validation sets and test sets, has changed in the era of deep learning. So whether the new best practices are doing that and whether your training set and your test come from different distributions, that’s happening a lot more in the era of deep learning. So how do you deal with that？ And if you’ve heard of end to end deep learning, you also learn more about that in this third course and see when you should use it and maybe when you shouldn’t. The material in this third course is relatively unique. I’m going to share of you a lot of the hard one lessons that I’ve learned, building and shipping(运送）, quite a lot of deep learninng products. As far as I know, this is largely material that is not taught in most universities that have deep learning courses. But I really hope you to get your deep learning systems to work well.
    In the next course, we’ll then talk aboout convolutional neural networks, often abbreviated CNNs. Convolutional networks or convolutional neural networks are often applied to images. So you learn how to build these models in course four.
    Finally, in course five, you learn sequence models and how to apply them to natural language processing and other problems. So sequence models includes models like recurrent neural networks abbreviated RNNs and LSTM models, sense for a long short term memory models. You’ll learn what these terms mean in course five and be able to apply them to natural language processing problems. So you learn these models in course five and be able to apply them to sequence data. So for example, natural language is just a sequence of words, and you also understand how these models can be applied to speech recognition or to music generation, and other problems.
    So through these courses, you’ll learn the tools of deep learning, you’ll be able to apply them to build amazing things, and I hope many of you through this will also be able to advance your career. So that, lets get started. Please go on to the next video where we’ll talk about deep learning applied to supervised learning.

   苟日新，日日新，又日新~