Day 2 #66DaysOfData
So if you read my last story, you’ll have know all about me (I guess), but now that the Intro parts are over. Let’s get our hands dirty
By failing to prepare you are preparing to fail — Benjamin Franklin
Machine Learning is a massive field, that keeps getting updated quite frequently, So I’m taking this field as more of a marathon rather than a sprint.
I sincerely don’t know what to do, but
It is better to start somewhere before you go everywhere — Ken Jee
I have seen a lot of roadmaps online, most with different content and approaches, some do a particular subject like Python first, while some prefer you learn Python later.
All these are great but may become overwhelming, So I decided to build a roadmap for myself, Breaking paths into components, and turning this components into goals.
For example, If I wanted to learn Python, my main goal of course would be “Learn Python”, but instead I’ll break it into more sustainable goals like “Learn Lists, Dictionaries and their Comprehensions this week”. This won’t make the learning more easier and more achievable, it would become more fun and it will stick with me.
I’ll be using Tina Huang’s “minimize effort maximize outcome method”, which basically means building projects from what I learned from my weekly goals/components.
But enough of all these chit-chat, let’s get down to business. Please note that all this are of personal preferences.
I also know Python before that’s why it’s not in my list, if you’re a newbie here, Learn Python from FreeCodeCamp
Also you can recommend me more courses or better ways to alter this roadmap!
PART A: Artificial Intelligence and Project Collaboration
This part covers learning what the concept of AI, what it is, what it can do, how it’s going to change the future. I was recommended to this by Smitha Kolan.
I also want to learn more on Git and GitHub, I don’t really know what a pull request is, and more of pushing, SHAs e.t.c
PART B: Data Analysis, Manipulation and Visualization, Data Tools
I’In all learn about Data Scuence Environments and Tools like Anaconda and Jupyter. I’ll also focus on how to collect data, clean it into meaningful ones, and visualise my insights. Exploratory Data Analysis would also be partially covered here. I’ll learn Numpy, Pandas, Matplotlib, Seaborn here.
PART C: Machine Learning Algorithms/ Techniques with Mathematics and Statistics
I’ll be spending most on my time on this section and may go to previous sections for refreshes. Since most of the mathematical aspects of my learning falls here, As I learn Machine Learning algorithms, I’ll learn their corresponding Math theories also, the reason being not to over-learn some math topics.
- Python for Data Science and Machine Learning Bootcamp(Paid) — Udemy
- Machine Learning Course by Andrew Ng(Free) — Coursera
- SentDex’s Machine Learning Playlist(Free) — YouTube
- Complete Machine Learning & Data Science Bootcamp 2021(Paid) — Udemy
- Machine Learning Crash Course(Free) — Google Developers
- Fast-AI Machine Learning Course(Free)
For the Mathematics and Statistics:
- StatQuest with Josh Starmer(Free) — Youtube
- Crash Course’s Statistics Playlist(Free) — Youtube
- Khan Academy (Free)
- Mathematics for Machine Learning(Free) — Book
PART D: Niches/Infinity and Beyond
I’ll focus on other aspects of A.I that interests me particularly Deep Learning and Computer Vision. This would be after I’ve started a Career in Machine Learning or I have made my skills monetized. This part really interests me and I can’t wait to get here, but it would take some time.
- Deep Learning by AndrewNg(Trial/Free- Student) — Coursera
- Python for Computer Vision with OpenCV and Deep Learning(Paid) — Udemy
- SentDex’s Deep Learning Basics Playlist(Free) — YouTube
- SentDex’s Deep Learning with Python(Free) — YouTube
That’s all for now folks. As you can see I’ve got a long way to go. Thanks for reading!!