I am a great fan of how Tesla is executing the problem of gathering data from the fleet of cars to train their net in efforts to build FSD, hence the image.

我非常熱衷于特斯拉如何執(zhí)行從車隊(duì)收集數(shù)據(jù)以訓(xùn)練他們的網(wǎng)絡(luò)以建立FSD并因此建立形象的問題。

Although Amazon recommends 1–2 years of experience developing, architecting, or running ML/deep learning workloads on the AWS Cloud, before sitting for the exam. But, with the right mindset for preparation, anyone can ace the exam in much less time.

盡管亞馬遜建議參加考試之前，建議在AWS云上開發(fā)，架構(gòu)或運(yùn)行ML /深度學(xué)習(xí)工作負(fù)載具有1-2年的工作經(jīng)驗(yàn)。 但是，只要有了正確的準(zhǔn)備思想，任何人都可以在更少的時(shí)間內(nèi)獲得考試的成功。

你真的喜歡ML嗎？ (Do you really like ML?)

If you don’t like Machine Learning, this story is not for you. But if you are new to ML and interested to learn, it will be useful.

如果您不喜歡機(jī)器學(xué)習(xí)，那么這個(gè)故事不適合您。 但是，如果您不熟悉ML并且有興趣學(xué)習(xí)，它將很有用。

I believe it becomes easy to learn a tool or concept when you really know the purpose of its existence or the impact of its existence. Knowing the purpose makes it clear and simple for you to map while you learn.

我相信，只要您真正了解工具或概念的存在目的或存在的影響，就可以輕松地學(xué)習(xí)它。 知道目的后，您在學(xué)習(xí)時(shí)就可以清楚，輕松地進(jìn)行映射。

If ML is entirely new to you? Go, do your homework on:

如果ML對您來說是全新的？ 快去做功課：

What is Machine Learning?

什么是機(jī)器學(xué)習(xí)？

What is a Distribution?

什么是分布？

What is a Model?

什么是模型？

Layman's understanding of steps to build an ML model?

Layman對構(gòu)建ML模型的步驟的理解？

What was the bottleneck for ML Systems before Cloud?

Cloud之前ML Systems的瓶頸是什么？

How the idea of Cloud, opened possibilities for ML?

云的想法如何為ML打開了可能性？

If you think the above ones are basic and boring, please try to cook some motivation by researching these.

如果您認(rèn)為以上內(nèi)容是基本且無聊的，請嘗試通過研究這些內(nèi)容來激發(fā)一些動(dòng)力。

How are folks at Tesla training their Autopilot?

特斯拉的員工如何訓(xùn)練他們的自動(dòng)駕駛儀？

What did it take to make a product like Apple Card?

制造Apple Card這樣的產(chǎn)品需要什么？

How does a Skydio Autonomous drone work?

Skydio自主無人機(jī)如何工作？

How is Siri suggesting you apps based on your usage patterns?

Siri如何根據(jù)您的使用方式向您推薦應(yīng)用程序？

How recommendation engine of YouTube works?

YouTube的推薦引擎如何工作？

How China ingeniously achieved mass surveillance using Facial Recognition?

中國如何通過面部識別巧妙地實(shí)現(xiàn)了大規(guī)模監(jiān)視？

How Apple FaceId works?

Apple FaceId如何工作？

What happens once you ask your Alexa to switch on your bedroom light?

一旦您要求Alexa打開臥室燈會怎樣？

How are big tech companies trying to achieve Level 5 Autonomous Driving?

大型科技公司如何努力實(shí)現(xiàn)5級自動(dòng)駕駛？

If you are in your 20s, you will surely know the app Shazam. Did you ever think of how Shazam works?

如果您20多歲，那么您肯定會知道該應(yīng)用程序Shazam。 您是否想到過Shazam的工作方式？

How do your insurance companies decide your premium?

您的保險(xiǎn)公司如何決定您的保費(fèi)？

How brilliant are the features of photo editing apps in 2020?

2020年照片編輯應(yīng)用程序的功能多么出色？

How tabbed inboxes in Gmail classify E-mails?

Gmail中的選項(xiàng)卡式收件箱如何對電子郵件進(jìn)行分類？

Ever heard of Amazon Go?

聽說過Amazon Go嗎？

How Visual Search works on Amazon?

視覺搜索如何在亞馬遜上工作？

How Doordash / Uber Eats / Postmates are determining an ETA for your order?

Doordash / Uber吃得如何/郵遞員如何確定您的訂單的預(yù)計(jì)到達(dá)時(shí)間？

How Google Photos curates a series of best photos from your albums

Google相冊如何策劃您相冊中的一系列最佳照片

Should I still continue with the list? The list just goes on.

我應(yīng)該繼續(xù)列出嗎？ 列表繼續(xù)。

Hopefully, this made you realize how deeply ML is responsible for the basic experiences we indulge every day in 2020, or at least you knew all this time that ML is the reason for these to be made possible. All right! In that case, you already are halfway through this goal, all the following steps are just to-dos and let you achieve the goal.

希望，這使您意識到ML對我們在2020年每天沉迷的基本體驗(yàn)負(fù)有多深的責(zé)任，或者至少您一直以來都知道ML是使之成為現(xiàn)實(shí)的原因。 行！ 在這種情況下，您已經(jīng)完成了這一目標(biāo)，以下所有步驟只是要做的事情，可以讓您實(shí)現(xiàn)目標(biāo)。

您是否偶然知道AWS？ (Did you happen to know about AWS already?)

Super! If you already knew about AWS or any Cloud platform, you are good.

超！ 如果您已經(jīng)了解AWS或任何云平臺，那就太好了。

Otherwise, I would suggest you know about Cloud, and also spend a few minutes skimming the AWS home page and the ML services they provide.

否則，我建議您了解Cloud，并花一些時(shí)間瀏覽一下AWS主頁及其提供的ML服務(wù)。

Here is a recent lecture by David J. Malan, which I deeply suggest for beginners. — Click here for the lecture

這是大衛(wèi)·J·馬蘭(David J. Malan)最近的演講，我向初學(xué)者強(qiáng)烈建議。 — 單擊此處進(jìn)行講座

Also, an introductory video of AWS.

另外，還有AWS的入門視頻。

I would suggest you take a course on the basics of AWS.

我建議您參加有關(guān)AWS基礎(chǔ)知識的課程。

All you need to be aware of are the benefits of Cloud and how the AWS Console looks.

您只需要了解Cloud的優(yōu)勢以及AWS Console的外觀即可。

AWS ML專業(yè)考試真正測試了您什么？ (What really AWS ML Specialty exam tests you?)

60% ML and 40% AWS.

60％ML和40％AWS。

Before we dive into the steps, let’s take a look at what the exam wants you to be good at?

在深入探討這些步驟之前，讓我們看看考試希望您擅長什么？

As Amazon Web Services quotes them:

正如Amazon Web Services引用的那樣：

1. Select and justify the appropriate ML approach for a given business problem

1.針對給定的業(yè)務(wù)問題選擇并證明適當(dāng)?shù)腗L方法

2. Identify appropriate AWS services to implement ML solutions

2.確定適當(dāng)?shù)腁WS服務(wù)以實(shí)施ML解決方案

3. Design and implement scalable, cost-optimized, reliable, and secure ML solutions

3.設(shè)計(jì)和實(shí)施可擴(kuò)展，成本優(yōu)化，可靠和安全的機(jī)器學(xué)習(xí)解決方案

Here, though only #1 talks about ML alone, without #1 it makes very little sense of #2 & #3. So it basically revolves around your understanding on the process of building an ML model — gathering the data, cleaning the data, normalizing the data, labeling the data (if required), ability to choose the model, most importantly tuning the model’s hyperparameters, deploying the model into production and about ensuring the performance in production.

在這里，盡管只有＃1單獨(dú)談?wù)揗L，但沒有＃1的話，對＃2和＃3的意義就很小。 因此，它基本上圍繞著您對ML模型構(gòu)建過程的理解-收集數(shù)據(jù)，清理數(shù)據(jù)，標(biāo)準(zhǔn)化數(shù)據(jù)，標(biāo)記數(shù)據(jù)(如果需要)，選擇模型的能力，最重要的是調(diào)整模型的超參數(shù)，部署將模型投入生產(chǎn)并確保生產(chǎn)績效。

So remember, more ML, less AWS.

因此請記住，更多的ML，更少的AWS。

多一點(diǎn)曝光？ (Little more exposure?)

If you have already known the basics, good. Otherwise, let me explain:

如果您已經(jīng)了解基礎(chǔ)知識，那就好。 否則，讓我解釋一下：

Layman對構(gòu)建ML模型的步驟的理解？ (Layman’s understanding of steps to build an ML model?)

Gather and Get the data

收集并獲取數(shù)據(jù)

Clean the data

清理數(shù)據(jù)

Label if required, make the data ready for use

如有需要，貼上標(biāo)簽，準(zhǔn)備好使用數(shù)據(jù)

Choose a model/approach/algorithm

選擇一個(gè)模型/方法/算法

Train the model using the data

使用數(shù)據(jù)訓(xùn)練模型

Re-iterate through this process until you get sufficient accuracy for the prediction

重新執(zhí)行此過程，直到獲得足夠的預(yù)測準(zhǔn)確性為止

Deploy the model to use it in Production (Enterprise level)

部署模型以在生產(chǎn)(企業(yè)級別)中使用它

那么，在AWS上還有什么可能呢？ (So, what more is possible on AWS?)

All the above steps can be done traditionally on-premise, basically on a powerful local machine or a bunch of servers using a combination of the following tools:

上述所有步驟通常都可以在本地進(jìn)行，基本上可以在功能強(qiáng)大的本地計(jì)算機(jī)或服務(wù)器上使用以下工具的組合來完成：

Python, Pandas, NumPy, Scikit_learn, Apache Spark MLlib, Google TensorFlow, Keras, PyTorch, Knime, Weka, Jupyter Notebooks, IBM Watson, Orange3

Python，Pandas，NumPy，Scikit_learn，Apache Spark MLlib，Google TensorFlow，Keras，PyTorch，Knime，Weka，Jupyter Notebooks，IBM Watson，Orange3

Similarly, by using the super ability of cloud providers, you can get them done seamlessly on the Cloud, say AWS.

同樣，通過使用云提供商的超強(qiáng)能力，您可以在云上無縫地完成它們，AWS說。

On AWS, there are a lot of services provided by AWS in general for various use-cases which helps to accomplish a truly end-to-end ML solution.

在AWS上，AWS通常為各種用例提供??很多服務(wù)，這有助于實(shí)現(xiàn)真正的端到端ML解決方案。

Mainly services like S3, Kinesis-Streams, Analytics, Firehose, Kinesis Video Streams, Glue ETL, Crawlers, Data Catalog, Athena, Database Migration Service, Data Pipelines; all these are provided for use-cases on Data Storage and migration which will make it easy for steps #1, #2, #3, #7.

主要服務(wù)包括S3，Kinesis-Streams，Analytics，Firehose，Kinesis Video Streams，Glue ETL，Crawlers，Data Catalog，Athena，數(shù)據(jù)庫遷移服務(wù)，數(shù)據(jù)管道； 所有這些都是針對數(shù)據(jù)存儲和遷移的用例提供的，這將使步驟＃1，＃2，＃3，＃7變得容易。

AWS also provides a suite of services with exclusive use-cases in Machine Learning which make it easier for #4, #5, #6. Just a part of them actually.

AWS還在機(jī)器學(xué)習(xí)中提供了一套包含專有用例的服務(wù)，這使得＃4，＃5，＃6變得更容易。 實(shí)際上只是其中一部分。

AWS made it so brilliant with Amazon SageMaker, which is a cloud machine-learning platform that takes care of abstracting a ton of software development skills necessary to accomplish the task while still being highly effective, flexible, and cost-efficient. To say, mainly it helps you focus on the core ML experiments and supplements the remainder necessary skills with easy abstracted tools. SageMaker supports frameworks like TensorFlow, PyTorch, Apache MXNet, Chainer, Keras, Gluon, Horovod, Scikit-learn, and Deep Graph Library. See the image below for the entire suite of ML Services provided by AWS.

AWS借助Amazon SageMaker取得了如此輝煌的成績 ， Amazon SageMaker是一個(gè)云機(jī)器學(xué)習(xí)平臺，可以抽象出完成任務(wù)所需的大量軟件開發(fā)技能，同時(shí)仍然保持高效，靈活和經(jīng)濟(jì)高效。 可以說，它主要是幫助您專注于核心ML實(shí)驗(yàn)，并通過簡單的抽象工具補(bǔ)充其余必要的技能。 SageMaker支持TensorFlow，PyTorch，Apache MXNet，Chainer，Keras，Gluon，Horovod，Scikit-learn和Deep Graph Library等框架。 有關(guān)AWS提供的整個(gè)ML服務(wù)套件，請參見下圖。

They came up with Amazon SageMaker Studio, the first fully integrated development environment (IDE) for machine learning, which otherwise makes it tedious to set up an end-to-end ML solution. A good point to mention, a new algorithm made by AWS — Random Cut Forest is also one of the algorithms provided on SageMaker.

他們提出了Amazon SageMaker Studio ，這是第一個(gè)用于機(jī)器學(xué)習(xí)的完全集成開發(fā)環(huán)境(IDE)，否則設(shè)置一個(gè)端到端的ML解決方案就很麻煩 。 值得一提的是，AWS制造的一種新算法-Random Cut Forest也是SageMaker提供的算法之一。

Machine Learning Suite provided by AWS | Source: AWSAWS提供的機(jī)器學(xué)習(xí)套件| 資料來源：AWS

AWS made it so easy by providing services built centric to highly popular use-cases in the market. Even if you are not aware of how Alexa is built, you can build your own Alexa with a combination of these services.

AWS通過提供針對市場中高度流行的用例構(gòu)建的服務(wù)，使之變得如此簡單。 即使您不了解Alexa的構(gòu)建方式，也可以結(jié)合使用這些服務(wù)來構(gòu)建自己的Alexa。

On a high level,

在高層次上

Alexa = Amazon Transcribe + Amazon Lex + Amazon Polly

Alexa = Amazon Transcribe + Amazon Lex + Amazon Polly

AWS上每個(gè)上述服務(wù)的描述： (Description of each of the above services on AWS:)

Amazon Transcribe — Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for developers to add speech-to-text capability to their applications. Using the Amazon Transcribe API, you can analyze audio files stored in Amazon S3 and have the service return a text file of the transcribed speech.

Amazon Transcribe- Amazon Transcribe是一種自動(dòng)語音識別(ASR)服務(wù)，使開發(fā)人員可以輕松地向其應(yīng)用程序添加語音到文本功能。 使用Amazon Transcribe API，您可以分析存儲在Amazon S3中的音頻文件，并使服務(wù)返回轉(zhuǎn)錄語音的文本文件。

Amazon Lex — Amazon Lex is a service for building conversational interfaces into any application using voice and text. With Amazon Lex, the same deep learning technologies that power Amazon Alexa are now available to any developer, enabling you to quickly and easily build sophisticated, natural language, conversational bots.

Amazon Lex- Amazon Lex是一項(xiàng)服務(wù)，用于使用語音和文本將會話界面構(gòu)建到任何應(yīng)用程序中。 借助Amazon Lex，現(xiàn)在任何開發(fā)人員都可以使用與Amazon Alexa相同的深度學(xué)習(xí)技術(shù)，從而使您能夠快速輕松地構(gòu)建復(fù)雜的自然語言對話機(jī)器人。

Amazon Polly — Amazon Polly is a service that turns text into lifelike speech, allowing you to create applications that talk and build entirely new categories of speech-enabled products

Amazon Polly- Amazon Polly是一項(xiàng)將文本轉(zhuǎn)換為栩栩如生的語音的服務(wù)，使您可以創(chuàng)建可以對話的應(yīng)用程序并構(gòu)建全新的語音支持產(chǎn)品類別

Made sense? Cool.

有道理？ 涼。

一旦您喜歡ML，就相當(dāng)簡單。 (Once you like ML, it is fairly simple.)

All the exam tests us is the ability to express the intuition behind basic ML algorithms.

我們所有考試的目的是能夠表達(dá)基本ML算法背后的直覺。

Here is a decent illustration of what it takes to build, train, and deploy a model.

這是構(gòu)建，訓(xùn)練和部署模型所需要花費(fèi)的一個(gè)很好的例證。

Machine Learning Workflow | Source: Google機(jī)器學(xué)習(xí)工作流程| 資料來源：谷歌

考試不需要什么，但需要學(xué)習(xí)： (What you don’t need for the exam, but need to learn:)

Nuances can be understood if you know these, otherwise getting your certification done will become just a mug up goal and soon you will give up for the convoluted stuff there.

如果您了解這些細(xì)節(jié)，就可以理解它們之間的細(xì)微差別，否則獲得認(rèn)證將只是一個(gè)艱巨的目標(biāo)，很快您將放棄那里的繁瑣事物。

Having a hands-on with Jupyter Notebook, Python Language, some libraries like Pandas, NumPy, Scikit_learn would be beneficial.

動(dòng)手使用Jupyter Notebook，Python語言和一些庫(例如Pandas，NumPy，Scikit_learn)將是有益的。

Knowing TensorFlow or Keras or PyTorch would be awesome.

知TensorFlow或Keras或PyTorch將是真棒。

什么是20小時(shí)？ (What are the 20 Hours about?)

Frank Kane and Stephane Maaraek are some brilliant folks in Cloud-based certifications. This is the best and optimal course that you can find in the market.

Frank Kane和Stephane Maaraek是基于云的認(rèn)證中的杰出人才。 這是您在市場上可以找到的最佳和最佳課程。

This course work is a decent culmination of just required pieces condensed in 10 hours of content. You might take a couple more hours to take notes and also to do some runs of active recall. This is why the title of this Medium story is tailored around hours, once you know the basics of ML, the purpose of ML, applications of ML and basics of AWS, all it takes is a 2x run of this course and finely taken notes and a couple of runs of Active Recall before you take your exam.

該課程的工作是將10小時(shí)內(nèi)容壓縮后的所需片段集結(jié)起來。 您可能需要花費(fèi)幾個(gè)小時(shí)做筆記，并進(jìn)行一些積極的回憶 。 這就是為什么這個(gè)中等故事的標(biāo)題會在幾個(gè)小時(shí)內(nèi)量身定制的原因，一旦您了解了ML的基礎(chǔ)知識，ML的目的，ML的應(yīng)用程序和AWS的基礎(chǔ)知識，所要做的只是本課程的2倍運(yùn)行，并仔細(xì)記錄筆記和參加考試前，需要進(jìn)行幾次“主動(dòng)召回”。

Boom! 20 Hours.

繁榮！ 20小時(shí)。

我準(zhǔn)備修改的轉(zhuǎn)儲： (The dump I prepared to revise:)

I made this cheat sheet to do some runs of active recall to help me persist my learnings, hope this helps. Remember, the sheet makes no sense before you actually learn, but becomes ultimately useful once you finish.

我制作了這份備忘單，進(jìn)行了一些積極的回憶，以幫助我堅(jiān)持學(xué)習(xí)，希望能有所幫助。 請記住，這張紙?jiān)谀嬲龑W(xué)習(xí)之前沒有任何意義，但是一旦您完成，它最終將變得有用。

Cheat Sheet

備忘單

Good luck to you!

祝你好運(yùn)！

End.

結(jié)束。

翻譯自: https://medium.com/swlh/how-i-prepared-for-aws-ml-specialty-in-20-hours-and-cracked-it-ad658bb778bc

總結(jié)

以上是生活随笔為你收集整理的我如何在20小时内为AWS ML专业课程做好准备并进行破解的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。