AhmedibrahimGH / Eng.-Mohamed-Hammad-AI-Recommendations

The repo contains books, tutorials and resources based on Eng Mohammed Hammad's recommendations.

Eng. Mohamed Hammad AI Recommendations

Self learning AI / Data Science curriculum.

About

This repository is intended to provide Artificial Intelligence, Machine Learning, and Deep Learning resources based on the recommendations of Eng. Mohamed Hammad.

Notice

Each resource is accompanied by the post at which it got recommended; so that you won't feel lost choosing one over the other, Make sure to check them out before beginning your journey.

The referring links for the [Book]s are being updated gradually.

You could download [Book]s directly from Library Genesis.

Content

• Prerequisites

  • Computational Thinking and Algorithms
  • Mathematics
  • Probability and Statistics

• Mini Roadmaps

  • The Shortest Path to Learning Data Science
  • Probabilistic Machine Learning
  • ML and Data Science
  • Roadmap for AI
  • Get three years of experience
  • Already have experience?

• Data Analysis

• Artificial intelligence and Machine Learning

• Neural Networks and Deep Learning

• YouTube AI Channels

• Posts

  • General posts
  • Machine Learning
  • Deep Learning

• Credits

Prerequisites

Computational Thinking and Algorithms

1. MIT's Introduction to Computer Science and Programming Using Python [Tutorial] [Beginner]
2. Stanford - Programming Paradigms [Tutorial] [Post Link] [Beginner]
3. Grokking Algorithms [Book] [Post link] [Beginner]
4. Algorithms Unplugged [Book] [Post 1], [Post 2], [Post 3] [Advanced]

Mathematics

1. MIT | Matrix Methods in Data Analysis, Signal Processing, and Machine Learning [Tutorial ] [Post link]
2. Mathematics for Machine Learning [Tutorial ] [Post link]
3. Discrete Mathematics and Its Applications - 7th Edition- [Chapter 10 - Graphs] [Post link]

Probability and Statistics

Why? [Post 1] [Post 2]

Books

1. Probability For Dummies [Book] [Post link] [Beginner]
2. An Introduction to Statistical Learning [Book] [Tutorial] [Post link] [Intermediate]
3. The Art of Statistics: Learning from Data [Book] [Post link]
4. The Elements of Statistical Learning [Book] [Post link] [Advanced]
5. Probabilistic Machine Learning [Kevin Murphy] [Book] [2012 Edition] [2022 Edition] [Post link]

Tutorials

1. Planting the Seeds of Probabilistic Thinking (Learn Probability role in Machine Learning) [Tutorial] [Beginner] [Post link]

   • Shakir Mohamed Planting the Seeds of Probabilistic Thinking Part 1 - YouTube

   • Shakir Mohamed Planting the Seeds of Probabilistic Thinking Part 2 - YouTube

   • Shakir Mohamed Planting the Seeds of Probabilistic Thinking Part 3 - YouTube

2. ANU Statistical Machine Learning 2022 COMP4670/8600 [Tutorial] [Post link]

Mini Roadmaps

The Shortest Path to Learning Data Science

✅ [First Check This Post] [Date: August 2022]

Now Check the Resources :

1. Intro to Data Science [Tutorial]
2. Python Data Science Handbook [Book], [Code]

Probabilistic Machine Learning

✅ [First Check This Post] [Date: August 2021]

Now Check the Resources Gathered in ORDER:

1. Eng. Hammad ITI Lecture
2. MIT RES.6-012 Introduction to Probability, Spring 2018 [Tutorial]
3. UC Berkeley CS 188 Introduction to Artificial Intelligence, Fall 2018 [Tutorial] [Arabic Edition]
4. Stanford CS221: Artificial Intelligence: Principles and Techniques [Lecture 11 to 15 only][Tutorial] [Post Link]
5. Daphne Koller - Probabilistic Graphical Models [Courses] [Post link]
6. Probabilistic Machine Learning: An Introduction [Kevin Murphy] (2022) [Book] [Post 1] [Post 2]
7. Gaussian Processes for Machine Learning, MIT Press [Book]

ML and Data Science

✅ [First Check This Post] [Date: June 2020]

Now Check the Resources Gathered in ORDER:

1. Machine Learning Fundamentals [Tutorial] [Unavailable now]
2. Undergraduate machine learning at UBC 2012 [Tutorial] [Slides]
3. CS480/680: Intro to Machine Learning - Spring 2019 - University of Waterloo [Tutorial] [Post 1], [Post 2]
4. Machine Learning 2013 [Tutorial]
5. Bayesian Reasoning and Machine Learning [Book]
6. Python Data Science Handbook [Book]

Roadmap for AI

✅ [First Check This Post] [Date: September 2021]

Now Check the Resources :

1. SYDE 522: Machine Intelligence (Winter 2018, University of Waterloo) [Tutorial] [Lecture notes] [Post 1], [Post 2]

2. CS480/680: Intro to Machine Learning - Spring 2019 - University of Waterloo [Tutorial] [Post 1], [Post 2], [Post 3]

3. CPSC 322: Introduction to Artificial Intelligence (UBC) [Tutorial] [Arabic Edition] [Post 1], [Post 2], [Post 3]

4. Artificial Intelligence_ A Modern Approach, 4th Edition (2021) [Book] [Post 1], [Post 2]

5. Machine Learning: A Probabilistic Perspective [Book] [Post 1], [Post 2],[Post 3] [Advanced]

Get three years of experience

✅ [First Check This Post] [Date: June 2022]

Now Check the Resources :

1. Artificial Intelligence By Example Acquire Advanced AI, Machine Learning and Deep Learning design skill [Book] [Post 1], [Post 2]
2. Mastering Machine Learning Algorithms, Second Edition [Book] [Post 1], [Post 2]

Already have experience?

✅ [First Check This Post] [Date: January 2021]

Now Check the Resources :

1. Mastering Machine Learning Algorithms, Second Edition [Book] [Post 1], [Post 2]
2. Artificial Intelligence By Example Acquire Advanced AI, Machine Learning and Deep Learning design skill [Book] [Post 1], [Post 2]
3. Artificial Intelligence_ A Modern Approach, 4th Edition (2021) [Book] [Post 1], [Post 2]
4. CPSC 322: Introduction to Artificial Intelligence (UBC) [Tutorial] [Arabic Edition] [Post 1], [Post 2], [Post 3]

Data Analysis

Books

1. Excel Data Analysis 2nd ed. 2019 Edition [Book] [Post link]

Artificial intelligence and Machine Learning

Books

1. EBooks (machinelearningmastery.com) [Post link]
2. Artificial Intelligence,A Guide to Intelligent Systems (2001) [Book] [Post link]
3. Artificial Intelligence_ A Modern Approach, 4th Edition (2021) [Book] [Post 1], [Post 2]
4. Pattern Recognition and Machine Learning (2006) [Christopher Bishop] [Book] [Tutorial] [Post 1], [Post 2], [Post 3], [Post 4], [Post 5]
5. Bayesian Reasoning and Machine Learning [Book] [Post link]
6. Python Data Science Handbook [Book] [Post link]
7. Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking [Book] [Post link]
8. Machine Learning: A Probabilistic Perspective [Book] [Advanced] [Post 1], [Post 2],[Post 3]
9. Bayesian Reasoning and Machine Learning [Book] [Advanced] [Post link]

Tutorials

1. MITx 6.00.2x, Introduction to Computational Thinking and Data Science [Tutorial] [What is DATA Science ? - Entry Course] [Post link]
2. Machine Learning Specialization - Andrew Ng [Specialization] [Post link]
3. Vrije Universiteit Amsterdam [Tutorial] [Post 1] [Post 2]
   • MLVU2019: VU Machine Learning 2019 [Tutorial] Post Link
   • Machine Learning @ VU | MLVU
   • Deep Learning @ VU | DLVU
4. Deep Learning Drizzle [Roadmap] [Post link] [Very Important 🔥]
5. Pattern Recognition Class (2012) [Post link]

Neural Networks and Deep Learning

Books

1. Neural Networks and Deep Learning By Michael Nielsen [Book] [Beginner] [Post 1] [Post 2]
2. Probabilistic Deep Learning with Python [Book] [Post link]
3. Neural Networks and Statistical Learning [Book] [Post link]
4. Evolutionary Approach to Machine Learning and Deep Neural Networks (Ch. 3)[Book] [Post link]
5. Graph Neural Networks [Book] [Post link]
6. Deep Learning Book by Aaron Courville, Ian Goodfellow [Book] [Post link]
7. Deep Learning for the Life Sciences [Book] [Post link]

Tutorials

1. NPTEL | Deep Learning- Part 1, IIT Ropar [Tutorial] [Post link]
2. NPTEL | Deep Learning - Part 2, IIT Madras [Tutorial] [Post link]
3. Neural networks class - Université de Sherbrooke | Hugo Larochelle [Tutorial] [Post link]
4. Neural Networks for Machine Learning by Geoffrey Hinton (Coursera 2013) [Tutorial] [Post link]
5. Theoretical Foundations of Graph Neural Networks (GNNS) [Tutorial] [Post link]
6. MIT Deep Learning in Life Sciences 6.874 Spring 2020 [Tutorial] Syllabus [Post link]
7. MIT Deep Learning in Life Sciences (Spring 2021) [Tutorial] [Post link]
8. CS 182: Deep Learning (Spring 2021) [Tutorial] Post Link
9. Deep Learning With PyTorch - Full Course [Tutorial] Post Link

YouTube AI Channels

1. Tübingen Machine Learning - [Post Link]
2. Kapil Sachdeva - [Post link]
3. Meerkat Statistics - [Post link]
4. Machine Learning and AI Academy - [Post link]
5. DeepFindr - [Post link]
6. The AI Epiphany - [Post link]
7. The Math Sorcerer

Posts

General posts

• فقدان الشغف.

• لو اتعلمت AI كويس هلاقي شغل ؟

• يا اخي خليني ابقي عاوز اقابلك.

• هتلاقي ناس كتير عاوزه تعمل كاريير شيفت الي AI.

• .اتعلم شوية Data Analysis

• لو بتشتغل Big Data.

• انت ليه دايما تقول ان Data Science علم عميق و تاكد المعني دا ؟

• .علشان تتعلم كويس يعني محتاج سنتين ما بين نظري و تطبيق

• لو الدراسة النظرية العنيفة في رياضيات و علوم احصاء و احتمالات مش خفيفة علي قلبك يبقي بلاش

• كورس ال AI اللي بيتدرس في كل جامعه تلاقي فيه ما يميزه عن جامعه اخري.

• متحاولش تتعلم من مصادر بتكتب ال Math من غير Visualization واضحة.

• المسائل اللي AI بتفريعاته بيحلها منقسمة الي نوعين.

• ايه النقطه اللي اعرف بيها اني كده عرفت و فهمت Probability and Statistics المطلوبة بشكل كافي ؟

• لو اتعلمت تقرأ Mathematical notations هتكمل

• اكثر الناس المرشحين جدا لفهم Machine Learning هم مهندسي كهرباء و بخاصة اتصالات

• ليه دايما هتلاقي الناس بتنصحك تتعلم من فيديوز الاول و بعدين من الكتب.

• Summer Schools مخصصه للخريجين

• صعب افتكر كل اللي بقراه و بتعلمه. لوكان دا اشكال بيواجهك ارجوك اقرا الكلمتين دول.

• هل اللي تعرفه من الساينس كافي و لا محتاج تكمل مذاكره ؟

• The Dark Side of Self Study.

• Ralph Kimball.

Machine Learning

• خليك شديد كده.

• لو بتتعلم Data Science او بتشتغل بيها او حتي عاوز تتعلمها كمل معايا شويه.

• بوست مهم لو حضرتك عاوز تتقدم كويس في DL,ML بمستوي اعلي من Graduate Level

• كلام مهم جدا للمهتمين ML,AI.

• طيب يا عمو انا عاوز ابقي من الفريق الاول اللي هم فعلا Data scientists , اعمل ايه ؟

• لو واجهتني مشكله جديده علي و دورت في الحل و لقيت ابحاث بتحلها مش بعرف اقرا الابحاث و بلاقي فيها طلاسم.

• تقريبا اي حد بيحاول يفهم Machine Learning كويس بيحتاج يتفسح في نصف العلوم اللي عملها البشر.

• انا ذاكرت ML كويس و فاهم كل الجوريثم بيعمل ايه. القضيه بقي اني شايفهم منفصلين و مش عارف ايه يستخدم مع ايه امتي.

• How to Become a Data Scientist.

• Data Scientist vs Data Analyst vs Data Engineer.

• Bayesian Analysis.

• Active Learning and Weak Learning.

• Unsupervised Learning with Graph Neural Networks

• The Hundred-Page Machine Learning Book

• #Probabilistic_Modeling Session 1

• #Probabilistic_Modeling Session 2

Deep Learning

• طول بالك للاخر لو بتستعمل DL.

• قبل ما تاخد قرار انك تهتم بال Deep Learning.

• لو حضرتك دربت شبكة علي صور قطط وكلاب وبعدين اديتها صورة مركب او قلم رصاص هيحصل ايه ؟

• علشان تفهم CNN,RNN لازم تتعلم Neural Networks كويس اوي اوي

• Generative Models اي محاولة لفهم شغلهم من سكة غير Probability هتفشل.

• وراء ابحاث ال Deep Learning المختلفة فكر واحد.

• ال SGD ليس مرتبطا بال DL.

• Transformer يحول كود من لغه برمجه الي اخري.

• ليه Gaussian شائع الاستخدام في تطبيقات ال Probability عبر مختلف التكنيكس ؟

• قبل اي محاولة لتعلم Probabilistic Graphical Models

• لو مستخدمتش PyTorch حتي الان جربه و مش هتندم.

• انا ودعت TensorFlow لصالح PyTorch من حوالي سنة.

• اذا كنت مهتم بال Deep Learning و عندك عنه Graduate Knowledge خليك معايا

• Graphical Models

• Neural Networks & Functional Programming.

• Accounting using Autoencoder Neural Networks.

• Symbolic Math - Deep Learning.

• Computational Graph (1), Computational Graph (2), Computational Graph (3)

• Universal Function Approximation.

• Symbolic Integration.

Shares

• دور علي الخبرة اللي هتبني عليها مستقبلك المهني، مش علي اسم ولا فلوس
• لو بدأت في حاجة كملها.
• Algorithms
• Deep Learning From Scratch I: Computational Graphs - sabinasz.net

Credits

This repository is nothing but a compilation of the great work done by Eng. Mohamed Hammad, and thanks to Eyad Hamza for this great idea. ;)