Many machine learning courses that target developers want you to start with algebra, calculus, probabilities, ML theory, and only then—if you haven't quit already—you may see some code.
I want you to know there's another way.
↓
I want you to know there's another way.
↓
2. For me, there's no substitute to seeing things working, trying them out myself, hitting a wall, fixing them, seeing the results.
A hands-on approach engages me in a way pages of theory never will.
And I know many of you reading this are wired just like me.
A hands-on approach engages me in a way pages of theory never will.
And I know many of you reading this are wired just like me.
3. I feel that driving a car is a good analogy.
While understanding some basics are necessary to start driving, you don't need to read the entire manual before jumping behind the wheel.
As long as you practice in empty parking lots and backroads, you'll be fine.
While understanding some basics are necessary to start driving, you don't need to read the entire manual before jumping behind the wheel.
As long as you practice in empty parking lots and backroads, you'll be fine.
4. As you make your way to public roads, you can start incorporating more of the theory that will help you stay safe.
At this point, that theory won't be lost on you: your hours behind the wheel will help you make the necessary connections.
Things will start clicking quick.
At this point, that theory won't be lost on you: your hours behind the wheel will help you make the necessary connections.
Things will start clicking quick.
5. I've talked to people struggling with derivatives that have no idea why or when they'll become helpful.
I've seen others memorizing what eigenvectors are, or manually transposing matrices because "that's what it takes."
Honestly, for the most part, it's not.
I've seen others memorizing what eigenvectors are, or manually transposing matrices because "that's what it takes."
Honestly, for the most part, it's not.
6. If you want to start, here is my recommendation:
• Develop a process to systematically break down problems.
• Find an hands-on course. Something that exploits your technical capabilities and puts them to good use.
Learn by doing.
• Develop a process to systematically break down problems.
• Find an hands-on course. Something that exploits your technical capabilities and puts them to good use.
Learn by doing.
7. I understand not everyone learns the same way.
If you prefer to start with the theory of things, that's great!
But if you "learn by example" like I do, lean on it and don't pay attention to those who claim "their way is the only way."
If you prefer to start with the theory of things, that's great!
But if you "learn by example" like I do, lean on it and don't pay attention to those who claim "their way is the only way."
8. There are many courses out there that introduce developers to machine learning with a practice-first approach.
"Practical Deep Learning for Coders" from @fastdotai is one that I usually recommend.
It's 100% free and you'll learn a ton.
"Practical Deep Learning for Coders" from @fastdotai is one that I usually recommend.
It's 100% free and you'll learn a ton.
9. Remember, everyone is different.
Pretending that there's only one way to learn machine learning, only one approach, only one method, is insane.
This is the way I learn. It has worked very well for me, and I hope it offers you a different perspective.
Pretending that there's only one way to learn machine learning, only one approach, only one method, is insane.
This is the way I learn. It has worked very well for me, and I hope it offers you a different perspective.
Follow me @svpino for more content on machine learning.
I write practical tips, break down complex concepts, and regularly publish short quizzes to keep you on your toes.
Stay tuned for more!
I write practical tips, break down complex concepts, and regularly publish short quizzes to keep you on your toes.
Stay tuned for more!
• • •
Missing some Tweet in this thread? You can try to
force a refresh
