I get asked about machine learning all the time.
Here are my answers to some of these questions: ↓
Here are my answers to some of these questions: ↓
Q: Where do I start?
Start by learning how to program.
Take your time. Usually, a solid year of Python experience will set you up for success.
Kaggle has a great introductory tutorial to get you started with Python.
Start by learning how to program.
Take your time. Usually, a solid year of Python experience will set you up for success.
Kaggle has a great introductory tutorial to get you started with Python.
Q: I already have plenty of Python experience. Now what?
For most people, I recommend the "Machine Learning Crash Course" created by Google or the "Intro to Machine Learning" from Kaggle.
If you are feeling adventurous, take "Machine Learning" from @AndrewYNg on Coursera.
For most people, I recommend the "Machine Learning Crash Course" created by Google or the "Intro to Machine Learning" from Kaggle.
If you are feeling adventurous, take "Machine Learning" from @AndrewYNg on Coursera.
Q: How about the math?
Most people can get started with high-school-level math.
From there, I usually recommend incorporating math as you need it.
(This is probably bad advice for aspiring researchers. I'm not one, so I don't know what I'm talking about.)
Most people can get started with high-school-level math.
From there, I usually recommend incorporating math as you need it.
(This is probably bad advice for aspiring researchers. I'm not one, so I don't know what I'm talking about.)
Q: Can I get a job after I finish a few online courses?
Probably not.
Most jobs require that you have experience building stuff. If all you do is watch videos and take notes, you'll have a hard time getting and keeping a job.
Build stuff.
Probably not.
Most jobs require that you have experience building stuff. If all you do is watch videos and take notes, you'll have a hard time getting and keeping a job.
Build stuff.
Q: Ok, I built some things. How do I get a job now?
Put everything you've done together in a portfolio. @DeepnoteHQ is the perfect place to make it look good.
Make sure you highlight this in your resume.
Here is an example: deepnote.com/@svpino
Put everything you've done together in a portfolio. @DeepnoteHQ is the perfect place to make it look good.
Make sure you highlight this in your resume.
Here is an example: deepnote.com/@svpino
Q: What's a good machine learning book?
My two favorite recommendations:
1. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: amzn.to/2KPuRAo
2. Deep Learning with Python: amzn.to/3lpNEPn
They are both worth every penny.
My two favorite recommendations:
1. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: amzn.to/2KPuRAo
2. Deep Learning with Python: amzn.to/3lpNEPn
They are both worth every penny.
Q: Is X a better course than Y?
It doesn't matter. Seriously.
The best course you can take is the one you are going to finish.
Most people waste too much time overthinking this step. Pick whatever is in front of you and get it done.
It doesn't matter. Seriously.
The best course you can take is the one you are going to finish.
Most people waste too much time overthinking this step. Pick whatever is in front of you and get it done.
Q: How long until I become an expert in machine learning?
Machine learning is a lifelong journey.
But who cares about "experts"? You can start providing value (and make money) in a much shorter timeline.
Machine learning is a lifelong journey.
But who cares about "experts"? You can start providing value (and make money) in a much shorter timeline.
Q: Do I need a Master's or a Ph.D. to get a job?
No, you don't. (Unless you want to be a researcher, in which case I told you I couldn't help you.)
For a job, showing demonstrable experience is usually enough.
(This is mostly the case in the US.)
No, you don't. (Unless you want to be a researcher, in which case I told you I couldn't help you.)
For a job, showing demonstrable experience is usually enough.
(This is mostly the case in the US.)
Q: Yesterday, my neighbor started talking about algorithms and data structures. Should I care about that?
You should.
Understanding computer science fundamentals is usually overlooked but highly beneficial.
You should.
Understanding computer science fundamentals is usually overlooked but highly beneficial.
Q: Which library should I start learning, Scikit-Learn, TensorFlow, or PyTorch?
It doesn't matter.
Don't focus on the tools. Focus on the problems and how to solve them.
Pick a course and let them guide you. Tools will come later.
It doesn't matter.
Don't focus on the tools. Focus on the problems and how to solve them.
Pick a course and let them guide you. Tools will come later.
Q: Do I need to buy a computer with a GPU?
You don't.
If you need them, you can access a GPU from any of the following online services:
• Google Colab
• Deepnote
• Kaggle
The large Cloud companies also give you access to GPU processing.
You don't.
If you need them, you can access a GPU from any of the following online services:
• Google Colab
• Deepnote
• Kaggle
The large Cloud companies also give you access to GPU processing.
Most courses will assign you projects that you can build.
Another option: pick a simple competition in Kaggle. There are thousands of them.
Third option: google “machine learning projects” and you’ll find an unlimited supply.
Another option: pick a simple competition in Kaggle. There are thousands of them.
Third option: google “machine learning projects” and you’ll find an unlimited supply.
https://twitter.com/Devathi_Nikhil/status/1446436943588257794
The Practical Deep Learning for Coders is a great starting point for developers that want to start right away.
It's focused on high-level code. Don't worry about the math, don't worry about the theory. All of that will come in due time.
It's focused on high-level code. Don't worry about the math, don't worry about the theory. All of that will come in due time.
https://twitter.com/prapandey031/status/1446459880722743299?s=20
• • •
Missing some Tweet in this thread? You can try to
force a refresh
