Hello and welcome.
背景：改變了傳統(tǒng)的網(wǎng)絡(luò)商業(yè)榜配，網(wǎng)絡(luò)搜索和廣告
As you probably know, deep learning has already transformed traditional internet businesses like web search and advertising.
幫助人們創(chuàng)造全新的方式的產(chǎn)品和事業(yè)
But deep learning is also enabling brand new products and businesses and ways of helping people to be created.
醫(yī)療：讀X光片卧檐，個(gè)性化教育，精準(zhǔn)農(nóng)業(yè)沪饺，自動駕駛汽車
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.
連接句
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 onto your resume` with confidence.
建立一個(gè)神奇的世界，AI魔力社會
Over the next decade, 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 society.
連接
So that, let's get started.
新的電力
I think that AI is the new electricity.
100年前，電力化改變了我們的社會：運(yùn)輸恩尾、制造熙兔、醫(yī)療悲伶、通信
Starting about 100 years ago, the electrification of our society transformed every major industry, every ranging from transportation, manufacturing, to healthcare, to communications and many more.
轉(zhuǎn)到AI
And today, we see a surprisingly clear path for AI to bring about an equally big transformation.
細(xì)化到深度學(xué)習(xí)
And of course, the part of AI that is rising rapidly and driving a lot of these developments, is deep learning.
總結(jié)：深度學(xué)習(xí)很受歡迎
So today, deep learning is one of the most highly sought after skills and technology worlds.
聯(lián)系到課程
And through this course and a few causes after this one, I want to help you to gain and master those skills.
介紹課程
So here's what you learn in this sequence of courses also called a specialization on Coursera.
一 神經(jīng)網(wǎng)絡(luò)基礎(chǔ)：神經(jīng)網(wǎng)絡(luò)、深度學(xué)習(xí) 4周
In the first course, you learn about the foundations of neural networks, you learn about neural networks and deep learning.
課程長度
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.
建立神經(jīng)網(wǎng)絡(luò)：深度神經(jīng)網(wǎng)絡(luò)住涉，如何用數(shù)據(jù)訓(xùn)練
But in this first course, you'll learn how to build a new network including a deep neural network and how to train it on data.
神經(jīng)網(wǎng)絡(luò)識別貓
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 running around in deep learning. And so, following tradition in this first course, we'll build a cat recognizer.
二 實(shí)踐
Then in the second course, you learn about the practical aspects of deep learning.
已經(jīng)學(xué)了什么：建立網(wǎng)絡(luò)麸锉、如何讓它有效
So you learn, now that you've built in your network, how to actually get it to perform well.
將學(xué)什么：超參數(shù)微調(diào)、正規(guī)化舆声、如何檢驗(yàn)偏差和變量花沉、先進(jìn)的優(yōu)化算法（Momentum動量方法柳爽、RMSprop、Adam優(yōu)化算法）
So you learn about hyperparameter tuning, regularization, how to diagnose price and variants and advance optimization algorithms like momentum armrest prop and the ad authorization algorithm.
很多調(diào)整碱屁，像黑魔法般建立神經(jīng)網(wǎng)絡(luò)
Sometimes it seems like there's a lot of tuning, even some black magic and how you build a new network.
簡單總結(jié) 3周 揭開黑魔法的神秘面紗
So the second course which is just three weeks, will demystify some of that black magic.
三 2周 構(gòu)建機(jī)器學(xué)習(xí)項(xiàng)目
In the third course which is just two weeks, you learn how to structure your machine learning project.
策略已經(jīng)變了
It turns out that the strategy for building a machine learning system has changed in the era of deep learning.
舉例：不太懂磷脯，是將數(shù)據(jù)分為訓(xùn)練集、測試集什么的嗎
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.
新的最佳做法娩脾，如果訓(xùn)練赵誓、測試集分布不同
So whether the new best practices are doing that and whether if you were 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?
端到端深度學(xué)習(xí)，適合情況
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.
比較獨(dú)特：深刻教訓(xùn)柿赊、建立并交付深度學(xué)習(xí)產(chǎn)品
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, quite a lot of deep learning products.
大學(xué)老師不會教
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.
四 卷積神經(jīng)網(wǎng)絡(luò) CNNs俩功，圖像處理
In the next course, we'll then talk about convolutional neural networks, often abbreviated CNNs. Convolutional networks or convolutional neural networks are often applied to images.
簡單總結(jié)，如何建立這些模型
So you learn how to build these models in course four.
五 序列模型及其應(yīng)用到自然語言處理
Finally, in course five, you learn sequence models and how to apply them to natural language processing and other problems.
循環(huán)神經(jīng)網(wǎng)絡(luò)：簡單的RNN碰声； LSTM模型诡蜓，長短期記憶模型
So sequence models includes models like recurrent neural networks abbreviated RNNs and LSTM models, sense for a long short term memory models.
解釋名詞并應(yīng)用到自然語言處理
You'll learn what these terms mean in course five and be able to apply them to natural language processing problems.
簡單總結(jié)，使用這些模型胰挑，應(yīng)用序列數(shù)據(jù)
So you learn these models in course five and be able to apply them to sequence data.
舉例：自然語言万牺，單詞的序列；語音識別洽腺、音樂生成
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.
專題總結(jié) 學(xué)習(xí)深度學(xué)習(xí)的工具
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.
連接下一課 監(jiān)督學(xué)習(xí)
So that, let's get started. Please go on to the next video where we'll talk about deep learning applied to supervise learning.
