You gotta think about this one carefully!

Imagine you go to the doctor and get tested for a rare disease (only 1 in 10,000 people get it.)

The test is 99% effective in detecting both sick and healthy people.

Your test comes back positive.

Are you really sick? Explain below 👇

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 short programming problems to stretch your imagination and make sure you are staying on your toes.

(Starting with the simple ones, they get more fun as you move towards the end.)

🧵👇

1. Write a function that reverses an array in place.

In other words, the function should not use an auxiliary array to do the work.

2. Write a function that finds the missing number in an unsorted array containing every one of the other 99 numbers ranging from 1 to 100.

3. Write a function that finds the duplicate number in an unsorted array containing every number from 1 to 100.

Only one of the numbers will appear twice.

4. Write a function that removes every duplicate value in an array.

There could be more than one value duplicated. You should remove all of them leaving a single copy of the value.

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.

One of the most popular activation functions used in deep learning models is ReLU.

I asked: "Is ReLU continuous and differentiable?"

Surprisingly, a lot of people were confused about this.

Let's break this down step by step: ↓

Let's start by defining ReLU:

f(x) = max(0, x)

In English: if x <= 0, the function will return 0. Otherwise, the function will return x.

If you draw this function, you'll get the attached chart.

Notice there are no discontinuities in the function.

This should be enough to answer half of the original question: the ReLU function is continuous.

Let's now think about the differentiable part.

A necessary condition for a function to be differentiable: it must be continuous.

ReLU is continuous. That's good, but not enough.

Its derivative should also exist for every individual point.

Here is where things get interesting.

We can compute the derivative of a function using the attached formula.

(I'm not going to explain where this is coming from; you can trust me on this one.)

We can use this formula to see whether ReLU is differentiable.

10 machine learning questions you should be able to answer.

I started experimenting with a questionnaire before interviewing candidates. Applicants submit a video or written answers to apply for the position.

Thread: Let's look at 10 of these questions.

The questionnaire solves a couple of problems:

1. Weeds out candidates that aren't ready for the job.

2. It significantly cuts down the time we spend talking synchronously.

One problem: It requires extra time from the candidate before the phone interview.

Here are some numbers on a job posting before using the questionnaire:

• 249 applicants
• 13 good applications

That's only 5%.

This sucks.

Numbers after using the questionnaire:

• 44 applicants
• 21 good applications

That's 47%.

This is much better.

I look at it this way:

Sooner or later, I'll ask these questions, and the candidate will have to answer them.

I'd rather give them space and the opportunity to think about their answers without any pressure.

Those who can't or don't want to answer won't apply. That's fine.

Right, screw it. Here's a thread on *that* FBLive by Alex Cairnie about #Govanhill. Lets do a watch-through shall we? (Mind, I'm a resident of Govanhill, and a sociologist. I'm also 5'3, and a visibly queer woman so if half his claims are true I should be living in terror)

00:30: Welcomes viewers and uses points out that his videos are only getting attention b/c they're 'horrific'. Directs folk to his Youtube page. So already clout hunting.

1:08: "I've been warned to stay out of Govanhill. I'm a marked man" (proceeds to use a beanie as a disguise)

1:30 "Laughing and joking aside, here's somebodys front garden." Proceeds to show litter and claim its thrown from windows and this is 'common'. I know a handful of streets with litter issues like this, but its neither common nor unique to #govanhill and other deprived areas.

2:10 "Don't be under any illusion I'm only showing you the bad bits" - only shows you the bad bits.

3:45: He's had offers of help, but hes said no because hes not responsible for 'anybody elses safety' Good lord.

5:01: "Its not that bad. But its not all good either" -Correct

6:00: TW: child abuse - He starts claiming to have been contacted by a health professional and told about child abuse 'in the area'. Huge ethical issues here as the 'professional' who has 'been in the game a long time' is reporting to Facebook Dude and not authorities.

After therapy sessions, it is occurring to me how my parents and maybe most desi parents don't really grow as parents. For example, a person would be a very different to a baby and to a teenager because the needs and vulnerabilities are so different.

But here, I feel that growth for parents stagnants sometime around when a child is 12-13. None of our parents really talk to us about puberty and growing up. None of us are taught or can talk about relationships because of moral reasons. So what do you have?

You have parents who are still parenting their adult children like kids, not apologising to us but asking us to eat, reminding us to wear jackets, locking up cars. They care. But they are coming from a care where the parent is always concerned about keeping the kid safe and alive

which imo really reduces the kind of parental advice and care one needs as an adult. Because adults know enough about the world to no longer be infantilized but we still have parents who expect us to be the same children because they're still the same kind of parents.

This is why so many of our parental relationships are strained or just based on civilities. We're forced to hide a lot from them because parents refuse to grow as parents and acknowledge us as adults. How many of us are still lectured, have curfews, other restrictions?

I know some people who seem (to me) more concerned with receiving VALIDATION for their mental health issues than solving them.

They seem to care most about other people BELIEVING their problems are real.

I'm curious about this.

Like, it's more important to them that people know how debilitating their anxiety is, than to overcome the anxiety.

Or it's important to them that others believe that they're actually depressed, not "just sad."

Or they want people buy into the narrative that they've been traumatized, and might be something like offended if someone minimizes that.

What do we make of this?

1. One possibility is that if solving the problems seems hopeless or even just really hard, you need external support to be able to cope.

If no one cuts you slack because of your mental health stuff, maybe you're in a really bad place, so you need people to believe you.

8 superfoods that will 10x your body mass:

1. Red Meat

Red meat is an excellent source of protein that aids in weight gain and muscular development.

It has leucine and creatine, which are substances important for increasing muscle building.

Protein and fat found in steak and other red meats contribute to weight gain.

2. Starchy Foods

Potatoes, sweet potatoes, corn, whole grain bread, oatmeal, whole wheat pasta, and brown rice are high-carbohydrate foods.

Carbohydrates, which have a protein-sparing effect, are essential for muscle growth along with proteins.

3. Eggs

Eggs are a powerhouse of protein, zinc, vitamins A, D, B 12, phosphorus, and folate.

Egg protein has a high biological value, which makes it the ideal post-workout snack.

There are 90 calories, 6.7 grams of fat, and 6.1 grams of protein in one large scrambled egg.

4. Fatty Fish

Essential fatty acids and proteins are abundant in fatty fish like salmon.

They aid in weight gain and immune boosting.

The finest source of omega-3 which is important for weight gain is found in these fish.

Spoke with my neighbour. A type 2 diabetic on medications and realized even now there is so much ignorance on this subject. I have done extensive research on this subject (was forced 2 after being diagnosed)

Here sharing it with you all. retweet it, it may save someone's life.

My Neighbour said his hba1c is 7. Everything is fine, he just needs to bring it below 6.9 and he would be fine.
That is just baloney! anything more than 5.6 will result in all kind of complications (Kidney failure,retina failure (blindness) amputations& heart attack etc etc

When i told him the benifits of intermittent fasting and fasting, My neighbour Nitin said, I cannot fast as doctor said i need to eat 5 -6 times a day.

FACT: If you are NOT on any insulin enhancing drugs. you can fast as much as you want. (metformin is OK)

to which he said These drugs r permanent & progressive, you can never stop using them.
FACT: if you can change your diet, you can change your sugar and insulin levels and no longer need these drugs. (advise not aplicable to type 1 diabetics, they wud always need insulin injection

Diet, I am on diet precribed by WHO.
FACT: Fuck WHO, and don't eat carbohydrates. infact another name of diabetes is carb intolerance. You can never acheive 5.6 or lower while eating your rice and roti.