"Introduction to Machine Learning Systems"
- FREE from MIT Press
- Authored by Harvard Professor
- 2048 Pages
To Get It Simply:
1. Retweet & Reply "ML"
2. Follow so that I will DM you.
WTF... First they said no to Elon Musk.
Then they built an AI that just shook the entire LLM industry.
– 27M parameters
– Trained on only 1000 examples
– Inspired by the human brain
– Beat Claude, o3-mini & Deepseek
You can’t afford to ignore this: 🧵
Cost to own vs rent has not been this out of whack in most people's lifetimes.
1980 was numerically worse, but it's still crazy how it went from a good time to buy, to a horrible time in 2 years 🚨🚨🚨
Ht Reventure Consulting YouTube
Lead by example. Then follow up with a verbal for max effect.
Yesterday at the splashpad:
Rock climbing wall was closed. I took my son and asked the lifeguard kid what was up with it.
“There’s been bees around for a couple weeks, kids have been getting stung. We’ve been asking for spray but no one’s got it.”
So I walk over to my wife. “Can you watch the kids, I’m gonna run out and get bee & wasp spray and take care of the rock wall nest bc clearly no one else is going to.”
So I ran to the dollar store and grabbed some spray. Came back and took care of business.
My son watched me take care of a problem that multiple life guards didn’t take care of for a couple weeks.
Then he and all the other kids, and of course myself, got to play on the rock wall.
So then, on the ride home, I explain to my kids that if no one is fixing the problem, and we are able to, we should fix the problem.
So the kids saw it, and they were told that it was intentional, not just a coincidence or accident.
In that conversation my son says “yeah it seems like our family is always using our big brain and the rest of the world is using small brain.”
You’re not wrong kid. It’s on us to show the world what right looks like.
A long time ago, I made a huge bet:
After 15 years of experience as a software engineer, I decided to focus on Machine Learning. It was tough, and most people thought I was crazy.
They were wrong.
That bet paid off and became one of my best decisions.
If you write software for a living, I want to show you in 2 minutes why learning Machine Learning is like going to the Hogwarts School of Witchcraft and Wizardry.
Let's start with a simple programming exercise:
"Write a function that returns zero if the supplied number is even or one if the number is odd."
If you are a developer, you know how to write this function. To keep things simple, we can represent the function like this:
y = f(X)
Here, "f" is the function that does the work, "X" is the input number, and "y" will be zero if the number is even or one if the number is odd.
The relationship between X and y is obvious in this example, so writing the function is straightforward.
But what happens when that's not the case? How would you solve any of the following problems?
• Predict tomorrow's temperature based on previous years.
• Predict a missing word in a sentence.
• Determine whether an image shows a dog or a cat.
That's where Machine Learning comes in! It gives you the tools to solve problems other software developers can't solve.
Programmers write rules and apply them to data to produce answers. But if those rules aren't obvious, they are stuck. With Machine Learning, we don't write the rules; we learn them from data. That's a superpower!
Look at the attached image from @fchollet's book. It's a good summary of this idea.
Think about how we learn: we look at things, discover patterns, and then generalize those ideas whenever we see something similar. That's the same principle behind Machine Learning: we use existing data to infer the answer to similar, future samples.
It's 2023. The best time to start learning Machine Learning is now.
I'd make the same bet all over again.
@JamieLSaunders I literally thought the same thing. And like what other people said…first thing I thought of for MAX, was Cinemax.
Maybe there will be a HBO Classic very soon! 😂
- Engineer: I invented this new thing. I call it a ballpen 🖊️
- TwitterSphere: OMG, people could write horrible things with it, like misinformation, propaganda, hate speech. Ban it now!
- Writing Doomers: imagine if everyone can get a ballpen. This could destroy society. There should be a law against using ballpen to write hate speech. regulate ballpens now!
- Pencil industry mogul: yeah, ballpens are very dangerous. Unlike pencil writing which is erasable, ballpen writing stays forever. Government should require a license for pen manufacturers.