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 👇

My recommendations to start with machine learning math:

• Statistics 110: Probability — Harvard University
• Essence of Linear Algebra — 3Blue1Brown
• Multivariate Calculus — Coursera

Links and 3 additional free resources here: https://t.co/fEmpmRKEvJ

If you are looking for more machine learning content, give me a follow and I’ll keep your feed interesting 😉.

I sat next to one of the smartest, most successful software engineers in the country for over 10 years.

Here's what I learned.

Fast is 10 times better than good.

9 out of 10 times, a "good enough" solution is all you need to unlock time, money, and attention.

Focus relentlessly on being first. Then take the time to be right.

Fast, then right.

Ship more frequently.

The faster you show your work to your users, the faster you'll hear their feedback, you'll adapt, and you'll ship again.

A question you should ask every day:

What can I do to ship this one day before planned?

Technical debt is a good thing.

Everyone hates technical debt. I think they don't know how to take advantage of it.

When used appropriately, technical debt means working on what truly matters and deferring anything that can wait.

No debt ⟶ You waited too long.

Ask, don't think.

People burn their time every day instead of asking for help.

You don't get extra points for working harder, especially when a little help will make you faster.

Time is your most valuable resource. Don't waste it.

Many machine learning courses that target developers want you to start with algebra, calculus, probabilities, ML theory, and only then—if you haven't quit already—you may see some code.

I want you to know there's another way.

↓

2. For me, there's no substitute to seeing things working, trying them out myself, hitting a wall, fixing them, seeing the results.

A hands-on approach engages me in a way pages of theory never will.

And I know many of you reading this are wired just like me.

3. I feel that driving a car is a good analogy.

While understanding some basics are necessary to start driving, you don't need to read the entire manual before jumping behind the wheel.

As long as you practice in empty parking lots and backroads, you'll be fine.

4. As you make your way to public roads, you can start incorporating more of the theory that will help you stay safe.

At this point, that theory won't be lost on you: your hours behind the wheel will help you make the necessary connections.

Things will start clicking quick.

5. I've talked to people struggling with derivatives that have no idea why or when they'll become helpful.

I've seen others memorizing what eigenvectors are, or manually transposing matrices because "that's what it takes."

Honestly, for the most part, it's not.

Machine learning education is broken.

If you are preparing for a research position, you are good. If you are looking to get out there and start solving problems, not even close.

Here are some thoughts so you can get ahead.

↓

Most classes, courses, and books cover the same road.

They start with a dataset. They finish with a working model. The focus is always on everything that happens in between.

Dataset → Model.

This is great, but not enough.

Real-life situations rarely start with a dataset, and they never end after you finish building your model.

Applying machine learning successfully is hard.

Here are a few examples that you should keep in mind.

First challenge: Properly framing up the problem.

If you don't understand the problem, you can't determine what data you need. If you don't understand the data, you can't build a good model.

I've never seen a company that had their data ready to go.

In fact, most of them don't even have data at all and need you to determine what exactly they should start collecting.

You usually have to go Problem → Potential Solution → Data.

Do you know what's better than a machine learning model?

Two models.

More than one model working together to solve a problem is called "an emsemble." A simple way to build this is having each model vote for an answer.

But there's a problem with this approach: ↓

I'm gonna focus here on image classification.

Let's assume you built two different models:

• Model 1: A ResNet model.
• Model 2: A one-shot model (Siamese network.)

They both solve the same problem, so you want to combine their results to pick the right answer.

The problem is that you have two models, so voting is not trivial.

What happens in this case?

• Model 1's answer: Class A
• Model 2's answer: Class B

Which one do you select?

Notice that this problem is not limited to an even number of models.

You could have 3 models, each giving you a different answer.

How do you decide which answer to choose?

There are multiple ways to approach this problem. I'll mention a few different ideas on this thread.

Important: Some of these ideas might not be feasible depending on your context. They have worked for me before on different situations, but every problem is different.

A staple of anti-lockdown conspiracism in yoga/wellness is that public health measures are oppressive, authoritarian, and stifling what it means to be human. Masks suppress identity and speech. Vaccines assault the sovereign body. Influencers must rise up against tyranny! /1

Ironically, pandemic management in economies where yoga/wellness is lucrative has been a neoliberal, choose-your-own-adventure mess in which centre-right governments barter with public health to enact a patchwork of half-measures that punish the poor and marginalized. /2

The goal is not universal health rights, or protecting medical systems, or saving as many lives as possible. The goal is to return to business-as-usual, using public health as a pit stop on a productivity race off a cliff. The ice caps aren’t melting fast enough, I guess. /3

Right-leaning governments, like influencers, have assessed the COVID threat with the magical bias of limitless optimism. Then they work to normalize COVID casualties as a new cost of doing business. *This* is what alt-healthers and Qamoms call “socialist”, or “communist”. /4

Centre-right governments and wellness influencers share a goal: get back to the optimism of making productivity heroic and consumption virtuous, without any reflection on structural issues of injustice, or what universal health care funding and standards would look like. /5

Masks. A short thread. In June last year my GP advised me that wearing a mask even for a short space of time would be harmful for me on two fronts. One - I have painful rosacea on my face. It’s a horrible condition and it’s lifelong. I can at times look scary!

Putting on a mask simply makes it worse. Two - I have hypertension. Manageable and controlled. GP also advises that mask wearing even for short periods can raise cortisol levels and make them dangerous to me.

On that basis and given the dreadful treatment us non-maskers have to suffer and to appease the abusers I have three times asked my GP to issue me with a letter relating to my conditions.

On each occasion she has said that there is no need. Whilst she won’t admit it straight up, all conversations suggest she’s been told not to. I happen to agree that no-one should need to reveal their medical history to anyone other than medical professionals responsible for me.

I’ve researched mask wearing in relation to what they are supposed to be used for ref *Covid* - I’m no thicko - I prepare risk assessments (and I’m qualified to do so) every day (or did) - and the evidence *for* is weak. Very weak.

Okay, let's start this hypersomnia thread!

[note - I am not looking for unsolicited advice.]

Idiopathic hypersomnia or narcolepsy (not the same, but similar) is very hard to describe to people.

When I say "I slept 10 hours last night and I'm still tired" I'm not bragging. 1/16

For me, the accommodations I need are about time. My body doesn't care what I want to do - when I want to wake up or be asleep. My body wants to wake up at 10-11am, and go to sleep at 3am, always.

Just a one hour shift in my sleep schedule can screw me up for days. 2/16

When I tell people that I'd really "prefer it" if we could meet at 10am or later, it's because getting up before that has consequences for me. Big consequences. Most people won't see them. Sometimes I still give in and say it's fine. It ruins 2-3 of my days, sometimes more. 3/16

Let me explain. When I am required to wake up at 9am, esp. in covid times working from home, my body pays me back for it later.

I'm going to show you ways this happens. I can usually withstand 1 day of waking up early, with some consequences, but 2 days in a row kills me. 4/16

Let's say this graph represents Day 1, the first time I am required to get up early. The y-axis is my level of Sleepiness. Any symptom listed higher up includes that symptom + every other symptom below it. Getting up that early means I can't listen or concentrate all day. 5/16

🧵 on Importance of correct indication of colonoscopic surveillance studies (English 🇺🇸🇬🇧)
@KM_Pawlak @KMonkemuller @drkeithsiau @JacquelineChuMD @PerelmansPearls @stevenbollipo @SWexner @DrBloodandGuts @ebtapper @DCharabaty @RashidLui @AdvaniRashmiMD @AtoosaRabiee @DrMohdZein

@GI_Guy @RodriguezParra_ @DrHarryThomas @TennysonMD @AustinChiangMD @KralJan @thomaskroner @alinkmd #GITwitter

1/ The implementation of screening and surveillance programs can reduce the incidence and mortality of

2 / But for these to be effective and to guarantee protection against CCR, they must meet a series of conditions. One of them is the correct indication for endoscopic studies for both screening and surveillance.

3 / According to a recent meta-analysis, the minority of patients who undergo colonoscopies have a correct indication, with less than 50% adherence to the surveillance intervals proposed by scientific