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 👇

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.

An introduction to one of the the most basic structures used in machine learning: a tensor.

🧵👇

Tensors are the data structure used by machine learning systems, and getting to know them is an essential skill you should build early on.

A tensor is a container for numerical data. It is the way we store the information that we'll use within our system.

(2 / 16)

Three primary attributes define a tensor:

▫️ Its rank
▫️ Its shape
▫️ Its data type

(3 / 16)

The rank of a tensor refers to the tensor's number of axes.

Examples:

▫️ The rank of a matrix is 2 because it has two axes.
▫️ The rank of a vector is 1 because it has a single axis.

(4 / 16)

The shape of a tensor describes the number of dimensions along each axis.

Example:

▫️ A square matrix may have (3, 3) dimensions.
▫️ A tensor of rank 3 may have (2, 5, 7) dimensions.

(5 / 16)

The two main machine learning techniques used in the industry today:

1. Gradient Boosted Trees
2. Deep Learning

Focus your time learning Scikit-Learn, XGBoost, and a Deep Learning library like Keras or PyTorch and you'll get the most for your time.

If you need to deal with structured data: Scikit-Learn + XGBoost.

If you need to deal with unstructured data (perceptual tasks): Keras or PyTorch.

Of course, there are many more techniques that will be helpful, but if you focus on these you'll be maximizing your ability to deliver value in the short term.

A topic that comes up in every interview.

Bias, variance, and their relationship with machine learning algorithms. One of the most basic concepts that you have to know by heart.

Here is a simple summary that you will easily remember.

↓

Every machine learning algorithm deals with 3 types of errors:

1. Bias error
2. Variance error
3. Irreducible error

There's nothing we can do about #3.

Let's focus on the other two.

↓ 1/5

"Bias" refers to the assumptions the model makes to simplify the process of finding answers.

The more assumptions it makes, the more biased the model is.

"Variance" refers to how much the answers given by the model will change if we use different training data.

If the answers stay the same regardless of the data, the model has low variance.

Often, linear models are high-bias, and nonlinear models are low-bias.

Example low-bias algorithms:
• Decision Trees
• SVN
• kNN

Example high-bias algorithms:
• Linear Regression
• Logistic Regression

All Women are at risk of getting Cervical Cancer. It often affect women over age 30.

Long-lasting infection with certain types of human papillomavirus (HPV) are the main cause of cervical cancer.

HPV is a virus that is passed from one person to another during sex.

A Thread 🚺

More than half of sexually active people might have HPV at some point in their lives, but few women will get CERVICAL CANCER.

Early Screening tests & the HPV vaccine can help prevent cervical cancer.

When cervical cancer is diagnosed early, it is highly treatable &....

2/cont.

associated with long survival and good quality of life.

Most (almost all) cervical cancers are caused by HPV.

There are many types of HPV.
Some HPV types can cause changes on a woman’s CERVIX that can lead to cervical cancer as time goes on, WHILE other types can cause genital

or skin WARTS . HPV is so common that most people get it at some time in their lives.

HPV usually causes no symptoms so you can’t tell that you have it. For most women, HPV might be SELF LIMITING (ie it will go away on its own); However, if it doesn't, there are a chances that

over time it may result to cervical cancer.

OTHER FACTORS CAN INCREASE YOUR RISK of CERVICAL CANCER —
•Having HIV/AIDS
•Smoking.
•Using Oral contraceptives (birth control pills) for a long time (5+ years)
•Having birth to many children (4+ yrs).
•Having many sexual partners

I think that, in the face of an ongoing global health emergency and a pressing need to reopen safely, some form of health pass is a reasonable option to consider. But debate is a good thing, so here are some brief thoughts on various concerns I've heard about them... [thread]

"A health pass discriminates against people who have refused the vaccine." No. A health pass should also support proof of test result for people who haven't been vaccinated, and exemptions for people who cannot be vaccinated (get vaccinated if you can though, for heaven's sake).

"A health pass is an invasion of privacy." No. A health pass should be privacy preserving, allowing you to prove your status to third parties without giving away personal data or letting them track you without your permission.

"A health pass is unfair to people without smartphones." No. A health pass should accommodate people without a smartphone, e.g. with a printable option as a fall-back (though for most of us, carrying a digital pass on our phone will be much more convenient).

"A health pass will become obsolete as the virus mutates." No. A health pass should actually give us more insight and flexibility to adjust our response as our knowledge of the virus, and the ways we test / treat / vaccinate for it, increases.

It's Monday AM post-@ASCO #GU21 & clinic starts in a couple of hours! Lots to process - I'll try to tackle optimal 1L tx for #kidneycancer. I'll make a case for cabo/nivo, leaning on the beautiful (& timely) tables below from @lalaniMD, @SoaresAndrey & @brian_rini (1/15)

What about IO/IO? We have long f/u w #CM214 data w nivo/ipi, no doubt (@AlbigesL et al in @myESMO Open). And treatment-free interval discussed by McDermott @BIDMChealth is no doubt impt. But we've known data not as impressive for favorable risk (2/15)

And furthermore, as @ERPlimackMD points out in another tweet, impt to look at primary PD rates (seen in @lalaniMD's table) - nivo/ipi at 19%!!! CR rate used to be something we highlighted w nivo/ipi, but now comparable across studies (3/15)

Okay now to the really tough stuff - comparing TKI/IO regimens. Something interesting I will add to @brian_rini @uromigos table above is the HR for PFS by INVESTIGATOR review. If the diff in HR for PFS by IND review caught your eye, this is even more striking (4/15)

I think INV-assessed PFS is impt, but if you're a skeptic, forget that argument. Turn instead to #QOL with axi/pembro. Kudos to @brian_rini @tompowles1 @ERPlimackMD et al for advocating for QOL in KN-426. @crisbergerot et al have taughts us the importance of these metrics. (5/15)