174 lines
14 KiB
Markdown
174 lines
14 KiB
Markdown
# Top-down learning path: machine learning for software engineers
|
||
Inspired by [Google Interview University](https://github.com/jwasham/google-interview-university).
|
||
|
||
_If you like this project, please give me a star._ ★
|
||
|
||
## What is it?
|
||
|
||
This is my multi-month study plan for going from mobile developer (self-taught, no CS degree) to machine learning engineer.
|
||
|
||
My main goal was to find an approach to studying Machine Learning that is mainly hands-on and abstracts most of the math for the beginner.
|
||
This approach is unconventional because it’s the top-down and results-first approach designed for software engineers.
|
||
|
||
Please, feel free to make any contributions you feel will make it better.
|
||
|
||
---
|
||
|
||
## Table of Contents
|
||
|
||
- [What is it?](#what-is-it)
|
||
- [Why use it?](#why-use-it)
|
||
- [How to use it](#how-to-use-it)
|
||
- [Don't feel you aren't smart enough](#dont-feel-you-arent-smart-enough)
|
||
- [About Video Resources](#about-video-resources)
|
||
- [Prerequisite Knowledge](#prerequisite-knowledge)
|
||
- [The Daily Plan](#the-daily-plan)
|
||
- [Machine learning overview](#machine-learning-overview)
|
||
- [Machine learning mastery](#machine-learning-mastery)
|
||
- [Machine learning is fun](#machine-learning-is-fun)
|
||
- [Machine learning: an in-depth, non-technical guide](#machine-learning-an-in-depth-non-technical-guide)
|
||
- [Stories and experiences](#stories-and-experiences)
|
||
- [Books](#books)
|
||
- [Kaggle knowledge competitions](#kaggle-knowledge-competitions)
|
||
- [Video](#video)
|
||
- [MOOC](#mooc)
|
||
- [Becoming an Open Source Contributor](#becoming-an-open-source-contributor)
|
||
- [My admired companies](#my-admired-companies)
|
||
|
||
---
|
||
|
||
## Why use it?
|
||
|
||
I'm following this plan to prepare for my near future job: Machine learning engineer. I've been building the native mobile application (Android/iOS/Blackberry) since 2011. I have a Software Engineering degree, not a Computer Science degree. I have itty bitty of basic knowledge about: Calculus, Linear Algebra, Discrete Mathematics, Probability & Statistics at university.
|
||
Think about my interest in machine learning:
|
||
- [Can I learn and get a job in Machine Learning without studying CS Master and PhD?](https://www.quora.com/Can-I-learn-and-get-a-job-in-Machine-Learning-without-studying-CS-Master-and-PhD)
|
||
- You can, but it is far more difficult than when I got into the field.
|
||
- [How do I get a job in Machine Learning as a software programmer who self-studies Machine Learning, but never has a chance to use it at work?](https://www.quora.com/How-do-I-get-a-job-in-Machine-Learning-as-a-software-programmer-who-self-studies-Machine-Learning-but-never-has-a-chance-to-use-it-at-work)
|
||
- I'm hiring machine learning experts for my team and your MOOC will not get you the job (there is better news below). In fact, many people with a master's in machine learning will not get the job because they (and most who have taken MOOCs) do not have a deep understanding that will help me solve my problems
|
||
- [What skills are needed for machine learning jobs?](http://programmers.stackexchange.com/questions/79476/what-skills-are-needed-for-machine-learning-jobs)
|
||
- First, you need to have a decent CS/Math background. ML is an advanced topic so most textbooks assume that you have that background. Second, machine learning is a very general topic with many sub specialties requiring unique skills. You may want to browse the curriculum of an MS program in Machine Learning to see the course, curriculum and textbook.
|
||
- Statistics, Probability, distributed computing, and Statistics.
|
||
|
||
I find myself in times of trouble.
|
||
|
||
AFAIK, [There are two sides to machine learning](http://machinelearningmastery.com/programmers-can-get-into-machine-learning/):
|
||
- Practical Machine Learning: This is about queries databases, cleaning data, writing scripts to transform data and gluing algorithm and libraries together and writing custom code to squeeze reliable answers from data to satisfy difficult and ill defined questions. It’s the mess of reality.
|
||
- Theoretical Machine Learning: This is about math and abstraction and idealized scenarios and limits and beauty and informing what is possible. It is a whole lot neater and cleaner and removed from the mess of reality.
|
||
|
||
I think the best way for practice-focused methodology is something like ['practice — learning — practice'](http://machinelearningmastery.com/machine-learning-for-programmers/#comment-358985), that means where students first come with some existing projects with problems and solutions (practice) to get familiar with traditional methods in the area and perhaps also with their methodology. After practicing with some elementary experiences, they can go into the books and study the underlying theory, which serves to guide their future advanced practice and will enhance their toolbox of solving practical problems. Studying theory also further improves their understanding on the elementary experiences, and will help them acquire advanced experiences more quickly.
|
||
|
||
It's a long plan. It's going to take me years. If you are familiar with a lot of this already it will take you a lot less time.
|
||
|
||
## How to use it
|
||
|
||
Everything below is an outline, and you should tackle the items in order from top to bottom.
|
||
|
||
I'm using Github's special markdown flavor, including tasks lists to check my progress.
|
||
|
||
I check each task box at the beginning of a line when I'm done with it. When all sub-items in a block are done,
|
||
I put [x] at the top level, meaning the entire block is done. Sorry you have to remove all my [x] markings
|
||
to use this the same way. If you search/replace, just replace [x] with [ ].
|
||
Sometimes I just put a [x] at top level if I know I've done all the subtasks, to cut down on clutter.
|
||
|
||
More about Github flavored markdown: https://guides.github.com/features/mastering-markdown/#GitHub-flavored-markdown
|
||
|
||
## Follow me
|
||
I'm a Vietnamese Software Engineer who are really passionate and want to work in the USA.
|
||
|
||
How much did I work during this plan? Roughly 4 hours/night after a long, hard day at work.
|
||
|
||
I'm on the journey.
|
||
|
||
|
||
|
||
## Don't feel you aren't smart enough
|
||
I get discouraged from books and courses that tell me as soon as I can that multivariate calculus, inferential statistics and linear algebra are prerequisites. I still don’t know how to get started…
|
||
|
||
- [What if I’m Not Good at Mathematics](http://machinelearningmastery.com/what-if-im-not-good-at-mathematics/)
|
||
- [5 Techniques To Understand Machine Learning Algorithms Without the Background in Mathematics](http://machinelearningmastery.com/techniques-to-understand-machine-learning-algorithms-without-the-background-in-mathematics/)
|
||
- [How do I learn machine learning?](https://www.quora.com/Machine-Learning/How-do-I-learn-machine-learning-1)
|
||
|
||
## About Video Resources
|
||
|
||
Some videos are available only by enrolling in a Coursera or EdX class. It is free to do so, but sometimes the classes
|
||
are no longer in session so you have to wait a couple of months, so you have no access. I'm going to be adding more videos
|
||
from public sources and replacing the online course videos over time. I like using university lectures.
|
||
|
||
## Prerequisite Knowledge
|
||
|
||
This short section were prerequisites/interesting info I wanted to learn before getting started on the daily plan.
|
||
|
||
- [ ] [Learning How to Learn](https://www.coursera.org/learn/learning-how-to-learn)
|
||
|
||
## The Daily Plan
|
||
|
||
Each subject does not require a whole day to be able to understand it fully, and you can do multiple of these in a day.
|
||
|
||
Each day I take one subject from the list below, read it cover to cover, take note, do the exercises and write an implementation in Python or R.
|
||
|
||
## Machine learning overview
|
||
- [ ] [A Visual Introduction to Machine Learning](http://www.r2d3.us/visual-intro-to-machine-learning-part-1/)
|
||
- [ ] [A Gentle Guide to Machine Learning](https://blog.monkeylearn.com/a-gentle-guide-to-machine-learning/)
|
||
- [ ] [Machine Learning basics for a newbie] (https://www.analyticsvidhya.com/blog/2015/06/machine-learning-basics/)
|
||
|
||
## Machine learning mastery
|
||
- [ ] [Applied Machine Learning with Machine Learning Mastery](http://machinelearningmastery.com/start-here/)
|
||
- [ ] [Python Machine Learning Mini-Course](http://machinelearningmastery.com/python-machine-learning-mini-course/)
|
||
- [ ] [Machine Learning Algorithms Mini-Course](http://machinelearningmastery.com/machine-learning-algorithms-mini-course/)
|
||
|
||
## Machine learning is fun
|
||
- [ ] [Machine Learning is Fun!](https://medium.com/@ageitgey/machine-learning-is-fun-80ea3ec3c471#.37ue6caww)
|
||
- [ ] [Part 2: Using Machine Learning to generate Super Mario Maker levels](https://medium.com/@ageitgey/machine-learning-is-fun-part-2-a26a10b68df3#.kh7qgvp1b)
|
||
- [ ] [Part 3: Deep Learning and Convolutional Neural Networks](https://medium.com/@ageitgey/machine-learning-is-fun-part-3-deep-learning-and-convolutional-neural-networks-f40359318721#.44rhxy637)
|
||
- [ ] [Part 4: Modern Face Recognition with Deep Learning](https://medium.com/@ageitgey/machine-learning-is-fun-part-4-modern-face-recognition-with-deep-learning-c3cffc121d78#.3rwmq0ddc)
|
||
- [ ] [Part 5: Language Translation with Deep Learning and the Magic of Sequences](https://medium.com/@ageitgey/machine-learning-is-fun-part-5-language-translation-with-deep-learning-and-the-magic-of-sequences-2ace0acca0aa#.wyfthap4c)
|
||
|
||
## Machine learning: an in-depth, non-technical guide
|
||
- [ ] [Overview, goals, learning types, and algorithms](http://www.innoarchitech.com/machine-learning-an-in-depth-non-technical-guide/)
|
||
- [ ] [Data selection, preparation, and modeling](http://www.innoarchitech.com/machine-learning-an-in-depth-non-technical-guide-part-2/)
|
||
- [ ] [Model evaluation, validation, complexity, and improvement](http://www.innoarchitech.com/machine-learning-an-in-depth-non-technical-guide-part-3/)
|
||
- [ ] [Model performance and error analysis](http://www.innoarchitech.com/machine-learning-an-in-depth-non-technical-guide-part-4/)
|
||
- [ ] [Unsupervised learning, related fields, and machine learning in practice](http://www.innoarchitech.com/machine-learning-an-in-depth-non-technical-guide-part-5/)
|
||
|
||
## Stories and experiences
|
||
- [ ] [The Machine Learning Mastery Method](http://machinelearningmastery.com/machine-learning-mastery-method/)
|
||
- [ ] [Machine Learning for Programmers](http://machinelearningmastery.com/machine-learning-for-programmers/)
|
||
- [ ] [Machine Learning in a Week](https://medium.com/learning-new-stuff/machine-learning-in-a-week-a0da25d59850#.tk6ft2kcg)
|
||
- [ ] [Machine Learning in a Year](https://medium.com/learning-new-stuff/machine-learning-in-a-year-cdb0b0ebd29c#.hhcb9fxk1)
|
||
- [ ] [Learning Path : Your mentor to become a machine learning expert](https://www.analyticsvidhya.com/learning-path-learn-machine-learning/)
|
||
|
||
## Books
|
||
- [ ] [Machine Learning for Hackers](https://www.amazon.com/Machine-Learning-Hackers-Drew-Conway/dp/1449303714)
|
||
- [ ] [Python Machine Learning](https://www.amazon.com/Python-Machine-Learning-Sebastian-Raschka-ebook/dp/B00YSILNL0)
|
||
- [ ] [Programming Collective Intelligence: Building Smart Web 2.0 Applications](https://www.amazon.com/Programming-Collective-Intelligence-Building-Applications-ebook/dp/B00F8QDZWG)
|
||
- [ ] [Machine Learning: An Algorithmic Perspective, Second Edition](https://www.amazon.com/Machine-Learning-Algorithmic-Perspective-Recognition/dp/1466583282)
|
||
- [ ] [Introduction to Machine Learning with Python: A Guide for Data Scientists(Pre-order)](https://www.amazon.com/Introduction-Machine-Learning-Python-Scientists/dp/1449369413)
|
||
- [ ] [Data Mining: Practical Machine Learning Tools and Techniques, Third Edition](https://www.amazon.com/Data-Mining-Practical-Techniques-Management/dp/0123748569)
|
||
- [ ] [Machine Learning in Action](https://www.amazon.com/Machine-Learning-Action-Peter-Harrington/dp/1617290181/)
|
||
|
||
## Kaggle knowledge competitions
|
||
- [ ] [Kaggle Competitions: How and where to begin?](https://www.analyticsvidhya.com/blog/2015/06/start-journey-kaggle/)
|
||
- [ ] [How a Beginner Used Small Projects To Get Started in Machine Learning and Compete on Kaggle](http://machinelearningmastery.com/how-a-beginner-used-small-projects-to-get-started-in-machine-learning-and-compete-on-kaggle)
|
||
- [ ] [Master Kaggle By Competing Consistently](http://machinelearningmastery.com/master-kaggle-by-competing-consistently/)
|
||
|
||
|
||
## Video Series
|
||
- [ ] [Machine Learning for Hackers](https://www.youtube.com/playlist?list=PL2-dafEMk2A4ut2pyv0fSIXqOzXtBGkLj)
|
||
- [ ] [Fresh Machine Learning](https://www.youtube.com/playlist?list=PL2-dafEMk2A6Kc7pV6gHH-apBFxwFjKeY)
|
||
- [ ] [Machine Learning Recipes with Josh Gordon](https://www.youtube.com/playlist?list=PLOU2XLYxmsIIuiBfYad6rFYQU_jL2ryal)
|
||
- [ ] [Everything You Need to know about Machine Learning in 30 Minutes or Less](https://vimeo.com/43547079)
|
||
|
||
## MOOC
|
||
- [ ] [Udacity’s Intro to Machine Learning](https://www.udacity.com/course/intro-to-machine-learning--ud120)
|
||
- [ ] [Coursera’s Machine Learning](https://www.coursera.org/learn/machine-learning)
|
||
- [Video only](https://www.youtube.com/playlist?list=PLZ9qNFMHZ-A4rycgrgOYma6zxF4BZGGPW)
|
||
|
||
## Becoming an Open Source Contributor
|
||
- [ ] [tensorflow/magenta: Magenta: Music and Art Generation with Machine Intelligence](https://github.com/tensorflow/magenta)
|
||
- [ ] [tensorflow/tensorflow: Computation using data flow graphs for scalable machine learning](https://github.com/tensorflow/tensorflow)
|
||
- [ ] [cmusatyalab/openface: Face recognition with deep neural networks.](https://github.com/cmusatyalab/openface)
|
||
- [ ] [tensorflow/models/syntaxnet: Neural Models of Syntax.](https://github.com/tensorflow/models/tree/master/syntaxnet)
|
||
|
||
## My admired companies
|
||
- [ ] [ELSA - Your virtual pronunciation coach](https://www.elsanow.io/home)
|