機(jī)器學(xué)習(xí) 深度學(xué)習(xí) ai

STRATEGY

戰(zhàn)略

• Learn theory + practical aspects.

  學(xué)習(xí)理論和實(shí)踐方面的知識(shí)。

  (At first get an overview of what you are going to learn).

  (首先獲得要學(xué)習(xí)的內(nèi)容的概述)。

• Gain a good hold/insight on each concept.

  掌握/理解每個(gè)概念。

• If you are not comfortable with maths at first; just get yourself comfortable with why we needed that maths part, and what is its O/P. Then, come to understand it later. Never skip any concept forever.

  如果您剛開始對(duì)數(shù)學(xué)不滿意，可以使用 只是讓自己對(duì)我們?yōu)槭裁葱枰獢?shù)學(xué)部分以及它的O / P感到滿意。 然后， 稍后再了解。 永遠(yuǎn)不要跳過任何概念。

• PRACTICE, PRACTICE, PRACTICE and PRACTICE!!!

  實(shí)踐，實(shí)踐，實(shí)踐和實(shí)踐！！！

  (

  (

  Coding comes into this phase)

  編碼進(jìn)入此階段)

• Understand boundary cases and failure concepts, to grap the concept of that topic.

  了解邊界情況和故障概念，以掌握該主題的概念。

• BELIEVE! Its easy;

  相信！ 它很簡單 ;

  Total of 150+ hours is good enough (5-10 hrs for 3-6 months)

  總共150個(gè)小時(shí)以上就足夠了(3-6個(gè)月5-10個(gè)小時(shí))

SPECIAL TIPS

特別提示

• For those facing difficulty in maths (like me :))

  對(duì)于那些面臨數(shù)學(xué)困難的人(像我一樣：)

  You need to consider math as

  您需要考慮數(shù)學(xué)

  Poetry + Art.

  詩歌+藝術(shù) 。

• Eqns :- Read in English sentence → Poetry

  Eqns ：-用英語閱讀→詩歌

• Geometry :-Visualize (human–visualizing creature) → Art

  幾何 ：可視化(人類可視化的生物)→藝術(shù)

Steps and Guidelines

步驟和準(zhǔn)則

You should note that, this is not the only way to approach for learning ML/DL. But this is really one of the best resource list for ML. You may have an option to pursue any certification course of your choice. It’s also good. I don’t discourage you for that. But, In case you want to save your money or you want to give ML a try and don’t want your money wasted in case you can’t continue. Then, you must follow some free available stuff online. And, trust me; you can never get a list better than this one. I have narrowed everything so precise so that you don’t get distracted elsewhere.

您應(yīng)該注意，這不是學(xué)習(xí)ML / DL的唯一方法。 但這確實(shí)是ML 最好的資源列表之一。 您可以選擇繼續(xù)自己選擇的任何認(rèn)證課程。 也不錯(cuò) 我不勸阻你。 但是，如果您想省錢，或者想嘗試一下ML，并且不想浪費(fèi)您的錢，以防萬一您無法繼續(xù)下去。 然后，您必須在線關(guān)注一些免費(fèi)的可用內(nèi)容。 而且，請相信我； 您再也找不到比這更好的清單了。 我已經(jīng)將所有內(nèi)容縮小到如此精確的程度，以使您不會(huì)在其他地方分心。

1) Programming language (Python or R)

1)編程語言(Python或R)

Book	Think python; ‘O’ reilly - Publication
Book	Learn python the Hard way; Zeads Hald
Site	www.Guru99.com/Python 3
Site	Python Tutorial, Tutorialspoint

書	想想python; 'O'reilly-出版
書	艱苦學(xué)習(xí)python; Zeads Hald
現(xiàn)場	www.Guru99.com/Python 3
現(xiàn)場	Python教程，Tutorialspoint

2) Probability and statistics

2)概率統(tǒng)計(jì)

Online course	Statistics & probability, Khan Academy
Blog	Basics of statistics for machine learning engineers I + II - -Joydeep Bhattacharjee
Slideshare	Probability basics for Machine learning (CSC2516) - Shenlong Wang*

在線課程	可汗學(xué)院統(tǒng)計(jì)與概率
博客	I + II機(jī)器學(xué)習(xí)工程師的統(tǒng)計(jì)基礎(chǔ)--Joydeep Bhattacharjee
幻燈片分享	機(jī)器學(xué)習(xí)的概率基礎(chǔ)(CSC2516)-Shenlong Wang *

3) Linear Algebra

3)線性代數(shù)

Online course - Linear Algebras; Khan Academy

在線課程-線性代數(shù)； 可汗學(xué)院

4) Calculus & Numeric Optimization

4)微積分與數(shù)值優(yōu)化

Online course	Multivariable calculus, Khan Academy
pdf	Derivatives, Back propagation and vectorization; Justin Johnson
pdf	Vectors, matrix and Tensor derivatives; Erik–learned Miller

在線課程	可汗學(xué)院多變量微積分
pdf格式	導(dǎo)數(shù)，反向傳播和矢量化； 賈斯汀·約翰遜(Justin Johnson)
pdf格式	向量，矩陣和張量導(dǎo)數(shù)； 埃里克·米勒

5) Brief of Machine learning

5)機(jī)器學(xué)習(xí)簡介

Book	what you need to know about machine learning - (Packt publication) – Gabriel A. Canepa
YouTube	Intro topics for Machine Learning – UB Vzard
Blog	Analyticsvidhya

書	您需要了解的有關(guān)機(jī)器學(xué)習(xí)的知識(shí)-(Packet出版物)-Gabriel A. Canepa
的YouTube	機(jī)器學(xué)習(xí)入門主題– UB Vzard
博客	Analyticsvidhya

Note: At this stage, I would like to personally recommend you a free available online course: Machine Learning @ Kaggle | Learn
- This will give you a basic to intermediate level of understanding in ML. Plus; you would learn How to compete at different platform like Kaggle, or Hackerearth.

注意：在此階段，我個(gè)人想向您推薦免費(fèi)的在線課程： 機(jī)器學(xué)習(xí)@ Kaggle | 學(xué)習(xí)
-這將使您對(duì)ML有了基本到中級(jí)的理解。 加; 您將學(xué)習(xí)如何在Kaggle或Hackerearth等不同平臺(tái)上競爭。

6) Classification and Regression technique

6)分類與回歸技術(shù)

Online course	Machine Learning, Andrew Ng; Course era/ YouTube
YouTube	Classification Techniques; UB Vzard
YouTube	Regression Techniques; UB Vzard
Blog	Analyticsvidhya

在線課程	機(jī)器學(xué)習(xí)，吳安德； 課程時(shí)代/ YouTube
的YouTube	分類技術(shù)； UB Vzard
的YouTube	回歸技術(shù)； UB Vzard
博客	Analyticsvidhya

7) Clustering Techniques

7)聚類技術(shù)

Same as above (6)
YouTube - Clustering techniques; UB Vzard

同上(6)
YouTube-群集技術(shù)； UB Vzard

8) Dimensionality Reduction

8)降維

Same as above
YouTube - Dimensionality Reduction Techniques; UB Vzard

同上
YouTube-降維技術(shù)； UB Vzard

9) Neural networks and deep learning

9)神經(jīng)網(wǎng)絡(luò)和深度學(xué)習(xí)

Online courses

在線課程

• Deep learning; Kaggle | Learn; Dan.S.Becker

  深度學(xué)習(xí)； Kaggle | 學(xué)習(xí); 丹·貝克爾

• Deep Learning, Andrew Ng; Course era/YouTube

  深度學(xué)習(xí)，吳安德； 課程時(shí)代/ YouTube

• Convolution Neural Networks; Stanford online/ YouTube (CS231n) (*If you want specifically CNN at broader scale.)

  卷積神經(jīng)網(wǎng)絡(luò) 斯坦福在線/ YouTube(CS231n)(*如果您想更廣泛地專門使用CNN。)

• Deep Learning A-Z^TM; Udemy

  深度學(xué)習(xí)AZ ^TM ; 烏迪米

• U B Vzard

  UB Vzard

10) Problem solving

10)解決問題

• Kaggle.com - solve problems end to end

  Kaggle.com-端到端解決問題

• Hackerearth.com - Participate in contests

  Hackerearth.com-參加比賽

• Analyticsvidhya.com - compete in Data Hacks and Student Data fest

  Analyticsvidhya.com-參與數(shù)據(jù)黑客和學(xué)生數(shù)據(jù)節(jié)

Understand why a technique is working (or) not working

了解為什么某項(xiàng)技術(shù)有效(或無效)

• Document /code (GitHub or blog)

  文檔/代碼(GitHub或博客)

• Portfolio of 5 or more case studies

  5個(gè)或更多案例研究的組合

• Read other’s blog or code

  閱讀他人的博客或代碼

11) Youtube series – UB Vzard

11)Youtube系列– UB Vzard

12) LinkedIn – Get in touch with Data Science community professionals. They will Help you, guide you and most importantly motivate you.

12)LinkedIn –與數(shù)據(jù)科學(xué)社區(qū)專業(yè)人士聯(lián)系。 他們會(huì)幫助您，指導(dǎo)您，最重要的是激勵(lì)您。

Note: Of course; this awesome article series @ IncludeHelp. Stay tuned for totally aligned and simplest platform for insightful knowledge at ease.

注意：當(dāng)然可以； 這個(gè)很棒的文章系列@ IncludeHelp 。 敬請關(guān)注完全一致且最簡單的平臺(tái)，以輕松獲取有見地的知識(shí)。

Conclusion

結(jié)論

At last, I would like to conclude that, don’t waste your crucial time wasting behind finding learning resources; although this is important before getting started. This bucket is really helpful and good enough to get you from Beginner to Advance Level. Find and mark out the best one and most suitable for you. And start over as soon as possible. And, always stick to that. You can take references from other resources too. A hearty apology, because U B Vzard is active on YouTube but it has not contained any ML videos yet; But, I am working on it with a leopard speed. You will have them ASAP. Don’t lose your hope. Trust me, it is easy. Catch you later in the next article. HAPPY LEARNING!

最后，我想得出一個(gè)結(jié)論，不要浪費(fèi)您的關(guān)鍵時(shí)間來浪費(fèi)學(xué)習(xí)資源； 盡管在開始之前這很重要。 這個(gè)存儲(chǔ)桶確實(shí)很有幫助，并且足以使您從初學(xué)者升到高級(jí)。 找到并標(biāo)記出最適合您的一種。 并盡快重新開始。 并且，始終堅(jiān)持這一點(diǎn)。 您也可以從其他資源中獲取參考。 致以誠摯的歉意，因?yàn)閁B Vzard在YouTube上很活躍，但尚未包含任何ML視頻； 但是，我正在以更快的速度進(jìn)行開發(fā)。 您將盡快擁有它們。 不要失去希望。 相信我，這很容易。 下一篇文章稍后會(huì)吸引您。 快樂的學(xué)習(xí)！

翻譯自: https://www.includehelp.com/ml-ai/how-to-learn-machine-learning-and-artificial-intelligence.aspx

機(jī)器學(xué)習(xí) 深度學(xué)習(xí) ai

總結(jié)

以上是生活随笔為你收集整理的机器学习 深度学习 ai_如何学习机器学习和人工智能？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。