Interviews aren't only about technical skills.

Here are some questions to help you prepare.

🧵👇

Beginners guide to start with machine learning.

What you need:

1. A programming language
2. A place to write and run code
3. A way to deal with data
4. A way to visualize results
5. A cool algorithm
6. An introductory course
7. A project to solve

Here are my recommendations.

Most people recommend Python to start.

I do too.

You can do machine learning with many different languages, but today, Python is the best option.

My advice: Get comfortable writing code before looking into machine learning.

You don't have to be a great developer to start.

But if you are, it helps.

Everything you know about building software is helpful to build machine learning systems.

Good developers have the odds in their favor.

"How much Python do I need to know before starting?"

If you ask, you aren't ready yet.

Ideal scenario: You should be comfortable building software. Most people get here within a year.

Let's move on to the 2nd item from the list: A place to write and run your code.

Get familiar with Google Colab.

• It's free.
• Requires no setup to start.
• It's available from anywhere.

Alternative: Kaggle.

The 8-step quick-start guide to learn Machine Learning.

🧵👇

1⃣ Start with Python 🐍

Yes, you can do other languages, but Python is by far the most straightforward option.

👇

2⃣ Get familiar with numpy, pandas, and matplotlib

These three libraries are probably the most common Python libraries you'll have to use every day.

(Even if you don't end up doing machine learning, these libraries are awesome and useful.)

👇

3⃣ Start using notebooks

Look into Jupyter or Google Colab.

Notebooks are essential for data scientists and machine learning practitioners. Most of the code you'll read and write will be in notebooks.

👇

4⃣ Find a problem (already solved)

In my opinion, the best way to start is by working through a problem —especially when you can learn from its solution.

Start with something simple. I usually recommend "Titanic" from Kaggle.

👇

11 key concepts of Machine Learning.

— Supervised Learning Edition —

🧵👇

😜

Before starting, remember that, if you follow me, one of your enemies will be immediately destroyed (and you'll get to read more of these threads, of course.)

And if you don't follow me, well, you just hurt my feelings.

😜

1. Labels

(Also referred to as "y")

The label is the piece of information that we are predicting.

For example:

- the animal that's shown in a picture
- the price of a house
- whether a message is spam or not

👇

2. Features

(Also referred to as "x")

These are the input variables to our problem. We use these features to predict the "label."

For example:

- pixels of a picture
- number of bedrooms of a house
- square footage of a house

👇

3. Samples

(This is also known as "examples.")

A sample is a particular instance of data (features or "x.") It could be "labeled" or "unlabeled."

👇

Some of the things I've learned in more than 20 years in the tech industry.

You need to hear these.

🧵👇

Listen to more people who don't look like you, don't speak your language, and don't come from the same place you do.

We aren't doing this near enough.

Small habits compound.

No small improvement is too small.

Just aim for something new every day, and you'll be surprised at the end.

Take responsibility.

It doesn't really matter how you feel, I'm sure you could have done better.

Always keep the big picture in mind and never lose the forest for the trees.

Be the person that pulls everyone out of the rabbit holes.

You are building a binary classification model to determine whether a picture shows a hot dog or not.

Which of the following activation functions is a good candidate for the output layer?

1. Rectifier Linear Unit (ReLU)
2. Leaky ReLU
3. Sigmoid
4. Softmax

Think about it.

The answer:

You could use either Sigmoid or Softmax.

I'm sure most of you picked Sigmoid. It's certainly the best way to approach this problem.

But Softmax is also an option —although unconventional for a binary classifier.

How about the other choices?

ReLU returns its input if positive, zero otherwise. Leaky ReLU is based on ReLU but with a slight slope for negative values.

ReLU and Leaky ReLU will always give us the previous layer output with no modifications if the input is always positive.

This doesn't help us.

Sigmoid has the ability to squash its input into a range that goes from 0 to 1.

This is good because we can now set a specific threshold for the output of a binary classifier.

Here is an example.

Any image with an output equal to or under 0.5 doesn't show a hot dog. Any image with an output above 0.5 shows a hot dog.

Sigmoid makes it very easy.

How about Softmax?

A Conspiracy Thread: Did Chaos Magick Break Reality?

What the hell is going on? Coronavirus, societal collapse, monoliths, aliens, what more do I need to say? Did William S. Burroughs actually achieve his goal of breaking reality? Let me explain.

William S. Burroughs was a member of Peter J. Carroll’s magickal organization, The Illuminates of Thanateros. They practiced chaos magick, a system of magick that denies all fixed models of reality. Basically they are encouraged to believe in whatever reality they want.

Burroughs was also an author who often used the cut-up method to write his novels, a technique that involves cutting up newspapers and magazines, putting the clippings in a hat, and then randomly pulling them out to create sentences.

Burroughs believed the cut-up method was a form of chaos magick that destabilized language, which he claimed was the main control mechanism of reality. Burroughs’ goal was to utterly destroy and dismantle all control systems and he thought his cut-ups could help him achieve this.

If you're feeling down lately, here's a quick test to figure out why:

👇

💖 Have you met up with your friends IRL this week?

🏋️‍♀️ Have you exercised today or yesterday?

🎨 Are you working on stuff that's meaningful to you?

🤝 Have you helped someone today with something you're good at?

How to become a SUCCESSFUL academic: a guide 1/n

How do I know how to become a successful academic? I don't, but I have received plenty of advice. As a good academic, I will just summarize what I have learned from listening

1) Be the ultimate collaborator but also don't be

Say yes to as many collaborations as physically possible: co-produce papers, LEARN, co-write grants, DISCUSS, it is all about synergy. But also, collaborations slow you down, have your own ideas! Just say no to collaborations

2) Be the methods ninja but also don't be

Science is only as good as its weakest link: don't be satisfied by applying the default analyses in the field. But also, don't let perfect be the enemy of the good and don't confuse reviewers. Just apply the default analyses in the field

3) Be the superstar teacher but also don't be

Professor means teacher, it is LITERALLY in the name. Being a good professor means being a superstar teacher. But also, focus on the science and minimize the hours of teaching, don't try to become a superstar teacher

Dear Jaime,

3 years ago your voice was silenced. I sent you and your brother to school to safely learn. I rushed you out the door that morning never expecting what would happen next. A school shooting!!! You were 14 and only a freshman in High School.

(1,11)

(2,11) Your brother Jesse survived…you did not.

You are on my mind every second of every minute of every day. I constantly relive your last seconds in my mind. Did you suffer? I will never know, but I fear that you did. Did I do enough to protect you?

(3,11) The answer is… No!!! I did not… and for that I will carry guilt for the rest of my life. My voice was not fighting the evil of gun violence before it was my daughter and for that I am sorry.

Today you should be a senior in school. We should be celebrating love.

(4,11) We should be looking at your senior pictures with you, watching you excitedly apply to colleges and helping you decide where to go. We should be excitedly looking forward to prom and I should be thinking about the advice I want to give you at graduation.

(5,11) While I am so happy to see all of your friends have these experiences, it breaks my soul to know that you are not part of that. Mom, Jesse and I won’t be able to watch you experience this with them. Every time I see posts with senior photos and college acceptances,

You wanna know the truth? My best friend just dropped me for no discernable reason in December when I was going through an unrelated mental breakdown (started in October) that required new treatment. To this day I have no clue what happened.

This has, without a doubt, been the most traumatic event that has ever happened to me. I had felt that maybe there was distance there, but I was trying to take care of myself. He reassured me he loved me just 1 week prior. Then, he said he was going to quit working with me.

He had been my business partner and literally helped me co-own my business. He requested his name be dropped from the company completely and that he needed to "put my family first" and find a different job. I don't know what that family first comment meant at all...

Then, he stopped communicating with me as frequently. This lasted a few days. He started acting extremely squirrelly and dodging direct questions. Very innocent questions like, "are you doing okay?" Again, this whole time I'm dealing with a genuine mental breakdown.

Last, he sent me a bizarre vague message, telling me that he didn't want to talk to me "in the foreseeable future" and cited some of the - honestly - most paranoid reasons for this. We live literally across the globe from one another. One of the things he accused me of was ...