We've all heard the horror stories.
Are you ready for machine learning math? Are you sure you can download a library, go through a course and make things happen?
This is some unsolicited advice.
↓ 1/10
Are you ready for machine learning math? Are you sure you can download a library, go through a course and make things happen?
This is some unsolicited advice.
↓ 1/10
Back then, we had to write custom training loops. Every time.
We all heard horror stories about the complexity of statistics and how ugly linear algebra was. This was a real thing.
The barrier to start with machine learning was high and full of thorns.
↓ 2/10
We all heard horror stories about the complexity of statistics and how ugly linear algebra was. This was a real thing.
The barrier to start with machine learning was high and full of thorns.
↓ 2/10
Today, things are different.
The lack of programming skills is a much bigger hurdle than not understanding how derivatives work.
Wanna have a better chance? Learn to code today. Worry about math tomorrow.
↓ 3/10
The lack of programming skills is a much bigger hurdle than not understanding how derivatives work.
Wanna have a better chance? Learn to code today. Worry about math tomorrow.
↓ 3/10
A couple of days ago, a friend and I reflected on how far he's gotten and how many problems he's solved.
He was scared to start.
He thought he needed to take a year and eat as many complex formulas as possible.
Nonsense.
↓ 4/10
He was scared to start.
He thought he needed to take a year and eat as many complex formulas as possible.
Nonsense.
↓ 4/10
We have been building frameworks and libraries for years now to knock down the gates.
Much of the work today is using high-level code that abstracts away a lot of the complexity.
This doesn't solve all the problems. But it reduces them significantly.
↓ 5/10
Much of the work today is using high-level code that abstracts away a lot of the complexity.
This doesn't solve all the problems. But it reduces them significantly.
↓ 5/10
Many people believe that you either understand how protons move in a wire or have no business changing an outlet.
That's fine. I don't need them to believe otherwise.
But I'm here to tell you that this is not true.
↓ 6/10
That's fine. I don't need them to believe otherwise.
But I'm here to tell you that this is not true.
↓ 6/10
And to make sure we are both on the same page:
Math is important. I have no questions about it.
But how much of it you need and when exactly you need it is debatable and depends on the work you need to do.
↓ 7/10
Math is important. I have no questions about it.
But how much of it you need and when exactly you need it is debatable and depends on the work you need to do.
↓ 7/10
I have two recommendations for you:
First, give machine learning a try.
Don't worry for now about the things *you think* you'll need. The time will come, and you can cross that bridge at that point.
↓ 8/10
First, give machine learning a try.
Don't worry for now about the things *you think* you'll need. The time will come, and you can cross that bridge at that point.
↓ 8/10
Second, I just sent my newsletter with a more thoughtful article that you should read.
What you'll get:
1. Math resource recommendations.
2. When and how you should learn it.
3. A little bit more encouragement.
→ digest.underfitted.io/archive/586995
↓ 9/10
What you'll get:
1. Math resource recommendations.
2. When and how you should learn it.
3. A little bit more encouragement.
→ digest.underfitted.io/archive/586995
↓ 9/10
Let me send you on your way with three more things:
• Don't put it out anymore. Start.
• Follow me if you need more encouragement.
• I'm really persistent. I promise.
We can do this together.
10/10
• Don't put it out anymore. Start.
• Follow me if you need more encouragement.
• I'm really persistent. I promise.
We can do this together.
10/10
• • •
Missing some Tweet in this thread? You can try to
force a refresh
