BC MACHINE LEARNING

Saved by @Alex1Powell

Santiago
@svpino 4 years, 6 months ago 1161 views

Save to PDF Share See On Twitter

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.

👇

5⃣ Focus on the analysis and not the code

In the beginning, spend your time and energy analyzing the problem and its solution.

Code is not important at this stage. Code can come later.

👇

6⃣ Start incorporating new algorithms

As you work through problems, start incorporating new algorithms into your toolset.

Here are a few great options to start:

1. Decision Trees
2. Linear regression
3. Logistic regression
4. Neural Networks
5. KNN

👇

7⃣ Get familiar with a general process to approach problems

Here is a good start:

1. Define the problem
2. Prepare the data
3. Spot-ccheck algorithms
4. Improve the results
5. Present the results

👇

8⃣ Pick a new problem and repeat

It shouldn't be surprising that the best way to improve is to practice and solve new problems.

If you don't have access to real-life problems, get familiar with Kaggle: everything you need will be there.

In the next coming weeks, I'll be posting a whole series of machine learning advice for people wanting to start.

Stay tuned!

More from Santiago

Santiago
@svpino

Free machine learning education.

Many top universities are making their Machine Learning and Deep Learning programs publicly available. All of this information is now online and free for everyone!

Here are 6 of these programs. Pick one and get started!

↓

Introduction to Deep Learning
MIT Course 6.S191
Alexander Amini and Ava Soleimany

Introductory course on deep learning methods and practical experience using TensorFlow. Covers applications to computer vision, natural language processing, and more.

https://t.co/Uxx97WPCfR

Deep Learning
NYU DS-GA 1008
Yann LeCun and Alfredo Canziani

This course covers the latest techniques in deep learning and representation learning with applications to computer vision, natural language understanding, and speech recognition.

https://t.co/cKzpDOBVl1

Designing, Visualizing, and Understanding Deep Neural Networks
UC Berkeley CS L182
John Canny

A theoretical course focusing on design principles and best practices to design deep neural networks.

https://t.co/1TFUAIrAKb

Applied Machine Learning
Cornell Tech CS 5787
Volodymyr Kuleshov

A machine learning introductory course that starts from the very basics, covering all of the most important machine learning algorithms and how to apply them in practice.

https://t.co/hD5no8Pdfa

Santiago
@svpino

What's machine learning?

Not a framework. Not a different language. Not the latest "cool" thing around the Internet.

Thread: Let me convince you that machine learning is the best thing since sliced bread 🍞.

Let's start with a simple exercise:

"Write a function that returns 0 if a supplied number is even or 1 if the number is odd."

If you are a developer, I'm sure you know how to write this function. It should be simple, right?

To avoid using a specific syntax, let's represent this function as follows:

y = f(X)

Where:
• X → The input number
• y → The result (0 if even, 1 otherwise)
• f → The function that does the work

We can now get to the interesting part.

If you are a programmer, writing this function is simple.

You know the relationship between X (the input number) and y (the output), so you can easily write the rules (the function.)

In machine learning, we don't write the rules. We learn them.

Imagine we had an algorithm that processes many samples (X → y), learns the relationship between them, and comes up with the correct rules.

We call these samples "training data," and they would like like this:

• 2 → 0
• 5 → 1
• 8 → 0
• 4 → 0
• 3 → 1
• ...

Advertisement

Santiago
@svpino

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.

Santiago
@svpino

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.

Santiago
@svpino

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.

More from Machine learning

Santiago
@svpino

For a long time, I didn't understand how to use Virtual Environments in Python 🐍.

If this is just, let's end it here and now: 🧵👇

[2] Virtual Environments let you deal with the dependencies that your code has with external Python libraries.

It avoids having conflicts when your projects depend on different versions of the same library.

👇

[3] Let's imagine that you are building your first Python project and you install the "requests" library:

pip install requests

You get version 2.24.0 installed in your system.

👇

[4] A month later, you decide to work on your second project. It also needs the "requests" library.

But the latest version is not 2.24.0 anymore.

Now version 3 is available, and that's the one you want to use!

👇

[5] You could upgrade your entire system to version 3, but then you'll be potentially breaking the first project you built that depends on 2.24.0!

Can you imagine this happening on a server with many more applications running?

👇

Kieran Snyder
@KieranSnyder

1 There's a chasm between an NLP technology that works well in the research lab and something that works for applications that real people use. This was eye-opening when I started my career, and every time I talk to an NLP engineer at @textio, it continues to strike me even now.

2 Research conditions are theoretical and/or idealized. A huge problem for so-called NLP or AI startups with highly credentialed academic founders is that they bring limited knowledge of what it takes to build real products outside the lab.

3 A product is ultimately a thing that people pay for - not just cool technology or user experience. But I’m not even talking about knowledge gaps in go-to-market work. I'm talking purely technical gaps: how you go from science project to performant + delightful user experience.

4 Most commoditized NLP packages solve well-understood problems in standard ways that sacrifice either precision or performance. In a research lab, this is not usually a hard trade-off; in general, no one is using what you make, so performance is less important than precision.

5 In software, when you’re making something for real people to use, these tradeoffs are a big deal. Especially if you’re asking those people to pay for what you’ve made (can’t get away from that pesky GTM thinking). They expect quality, which includes precision AND performance.

Advertisement

Jan Giacomelli
@jangiacomelli

🤔 Python generators

What are they? How to use them?

#Python

🧵Let's find out 👇

1️⃣ Python generators are lazy iterators delivering the next value when their .next() is called.

They are created by using the yield keyword

next() can be called explicitly or implicitly inside for loop

They can be finite or infinite

2️⃣ yield - where a value is sent back to the caller, but the function doesn’t exit afterward as with the return statement

The state of function is remembered.

For example, the number is incremented and sent back from yield at the consecutive call next()

3️⃣ Generator stores only the current state of the function - it generates next element on next() call and forgets the previous one -> it saves memory

For example, we don't need to store 1mio elements in memory to do something with each element

4️⃣ When you call a generator function generator object is returned - it's not executed yet

It executes only when next() is called

For example, that's why Exception is raised only on the next() call

IM POCUS Focus
@IMPOCUSFocus

A tweetorial on optimal machine settings for B line image acquisition, with a focus on: focal position at pleura, harmonics off, and increased far gain.

Inspired/based on the recent article - https://t.co/vv2xBSZm6N
@cameron_baston @IsaacMatthiasM1

#POCUS #IMPOCUS

1/18

Let's start with some polls
We will stick to low frequency probes here (i.e. curvilinear and phased array - linear has its own purpose for detailed pleural assessment)

Which preset do you prefer for B line assessment?

2/

What depth do you typically set?

3/

After selecting preset and selecting depth, do you ever adjust any other machine settings to optimize B line assessment?

4/

Importantly, there is no right answer to the above questions!

We won't discuss much about preset or probe type. But we will discuss machine settings to optimize B line quality, based on
1) Theory based on physical basis of B lines
2) In vitro study
3) Study in patients

5/

Pratham Prasoon
@PrasoonPratham

Are you planning to learning machine learning this year?

These are the Python frameworks you need to learn as an absolute beginner.

🧵👇

It can be overwhelming seeing all the machine learning frameworks at once and not even knowing what they do.

I made this thread so that your machine learning journey becomes just a little bit easier.

(2 / 11)

This thread will only focus on Python frameworks.

Why?
Because Python is the most common path into machine learning.

( If you have experience with any other language then learning Python will not be difficult at all. )

(3 / 11)

Here's the entire list:

- Pandas
- Numpy
- Matplotlib
- TensorFlow
- PyTorch
- Keras
- Scikit Learn

Let's see what they do.

(4 / 11)

You'll have to interact with csv files or databases on a regular basis to access data in machine learning, pandas helps you do just that.

The cool thing about Pandas is that it actually doesn't change the original data...

(5 / 11

You May Also Like

Justin Kan
@justinkan

1/ Throughout my startup career, I’ve seen many founders have an aversion to sales. This is a mistake that can kill your startup.

2/ Sales is often viewed as either a saving grace or proof that the product isn’t good enough (because it should sell itself). Neither are ever true. Some common mistakes that result in...

3/ Mistake 1: Hire a sales rep before reaching product/market fit to get your initial batch of customers. This is a mistake because founders need to work through their MVP with early adopters to truly understand what it is they’re selling.

4/ Mistake 2: Reach product/market fit, need to scale, and rely entirely on self-serve. For enterprise products that require big commitments and internal shifts, almost no product is self-explanatory enough to sell itself.

5/ Mistake 3: Make a first sales hire who isn’t scrappy enough to help mold the sales process from scratch. Some salespeople are amazing at their jobs, but not cut out to establish the processes that others end up following. This skillset is what @rdedatta calls a “sales ninja”.

Dr. Jane Clare Jones
@janeclarejones

So, on the subject of bonkers hyperbolic pretzeling over the Bell judgement, Grace 'destroy books I don't like & make inappropriate jokes about sterilising teenage girls' Lavery has some thoughts.

Tell me why my feminism is wrong Grace.

Oh

Well, if anyone thought the Bell judgment was going to make TRAs reconsider making massively overblown claims with no evidence backed up with nothing but a thick wadge of emotional blackmail.... HAHAHA, no one thought that.

A high court in the UK made a delimited judgment about teenager's ability to consent to puberty blockers. This puts all trans people everywhere in the world at risk.

Because if any human anywhere has any thoughts that deviate in any way from the rote line dictated by

the trans rights movement, this puts all trans people everywhere in mortal danger.

Let's be honest Grace. It doesn't put trans people at risk. It puts trans ideology at risk. Because trans ideology depends on the idea of innate gender identity, and the trans child is the

necessary material evidence of the ontology of gender identity.

That is, children are being medicalised to provide evidence to underwrite adults identities.

Nothing to see here.

Advertisement

$Liz (Welsh) Beechinor \U0001f605$

Liz (Welsh) Beechinor ...
@LizTweetsTech

My dad led an organization of over 300,000 employees.

When I took on my biggest marketing & events team to date (35 employees) I asked him how the *heck* he did it. Here's what he said and what helped me every day. 🧵

Remember you're leading all the employees under you, but you're not *managing* them all. You're managing your direct reports, which should be 5-7 individuals max. Focus on them.

When you interact with the employees you don't manage directly, get to know them as people first, that'll be the most valuable information in leading them. Remembering everything you learn about them is hard, but doing so will make you a superhero.

If you're not going to empower the managers under you, why do you have them? If you see room for improvement, let the manager know and let them make the change on their teams and come to you with questions/concerns. This will save you SO much time.

If you're the smartest person in any room - you're doing it wrong. As a leader, your job is bringing together the best people to get the job done - your skillset is identifying those people, not being one of them.

Patrick McKenzie
@patio11

Some people really benefit from hearing advice that everyone knows, for the same reason we keep schools open despite every subject in them having been taught before.

In that spirit, here's some quick Things Many People Find Too Obvious To Have Told You Already.

Your idea is not valuable, at all. All value is in the execution. You think you are an exception; you are not. You should not insist on an NDA to talk about it; nobody serious will engage in contract review over an idea, and this will mark you as clueless.

Technologists tend to severely underestimate the difficulty and expense of creating software, especially at companies which do not have fully staffed industry leading engineering teams ("because software is so easy there, amirite guys?")

Charge more. Charge more still. Go on.

The press is a lossy and biased compression of events in the actual world, and is singularly consumed with its own rituals, status games, and incentives. The news necessarily fails to capture almost everything which happened yesterday. What it says is important usually isn't.

Companies find it incredibly hard to reliably staff positions with hard-working generalists who operate autonomously and have high risk tolerances. This is not the modal employee, including at places which are justifiably proud of the skill/diligence/etc of their employees.

$Murray \U0001f1fa\U0001f1f8$

Murray 🇺🇸...
@Rothbard1776

NEW: @SidneyPowell1 radio interview w/ @toddeherman "The new report has a truckload of evidence of foreign interference in the election in it. That's what people seem to want to deny, even though the FBI & CISA ... issued an advisory and alert back on Oct. 30th & updated on

2/ Nov. 3rd, so for them to deny that now is absolutely absurd. Plus, we have an affidavit from an expert cyber-warfare [individual] who even shows the diagram of all the attacks coming in. We know that the VPN ... the Dominion people left those open and unencrypted on the night

3/ of the election, so that anybody could get in. We know that the packets of information went to Serbia [note: over 100 Dominion employees scrubbed there LinkedIn profiles of any affiliation with the company after the election, many of whom were in Serbia], Liechtenstein,

4/ Spain, Venezuela, Hunan, China & Hong Kong. There was traffic all over into our election system that is supposed to be self-contained, not accessible by the internet at all. We have witnesses who document that it was connected to the internet. We have a study out of

5/ [the Dominion voting system in Antrim] MI, they know that it was connected to the internet. They erased their audit files & their adjudication files, where they dumped over 68% of their ballots into a bin that they call "adjudication" [that would've been thousands + thousands