BC MACHINE LEARNING

Saved by @CodyyyGardner

Jan Giacomelli
@jangiacomelli 5 years, 5 months ago 1385 views

Save to PDF Share See On Twitter

🤔 Python decorators

What are they? How do you use them?

🧵 Let's find out 👇

1️⃣ Decorator is a function or a class that wraps another function or class modifying its behavior.

So how does that work?

The first thing to know is that everything in Python is an object - functions too

2️⃣ That means they can be passed to another function as an argument or returned from a function

Functions that take other functions as an argument are called higher-order functions

3️⃣ In Python, you can define a function inside other function - such functions are called inner functions

4️⃣ To create a decorator you just need to apply all of that together

log_enter_leave is a decorator.

my_function is the function.

To alter my_function's behavior we reassign it applying log_enter_leave decorator.

5️⃣ To simplify usage of decorators Python offers us syntactic sugar

A "pie-decorator" syntax using @

@decorator_name

6️⃣ The only problem here is that my_function now identify as the wrapper function

To solve that we just need to use wraps from functools

7️⃣ You can decorate classes too.

For example, you can dataclass decorator on your class to automatically generate its __init__ and __repr__ methods

8️⃣ You can also use a class as a decorator

Decorator class needs methods:
- __init__
- __call__ (it makes class callable)

9️⃣ For example, decorators are used for registering view functions to the Flask application

1️⃣0️⃣ Read more:

https://t.co/eBMh1Gv0xZ

https://t.co/2YdA2ZIQoV

https://t.co/Wb0jSjmzlc

1️⃣1️⃣ Script with all of the examples:

https://t.co/Tw1qrbN0nN

More from Machine learning

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/

John Burn-Murdoch
@jburnmurdoch

Really enjoyed digging into recent innovations in the football analytics industry.

>10 hours of interviews for this w/ a dozen or so of top firms in the game. Really grateful to everyone who gave up time & insights, even those that didnt make final cut 🙇‍♂️ https://t.co/9YOSrl8TdN

For avoidance of doubt, leading tracking analytics firms are now well beyond voronoi diagrams, using more granular measures to assess control and value of space.

This @JaviOnData & @LukeBornn paper from 2018 referenced in the piece demonstrates one method https://t.co/Hx8XTUMpJ5

Bit of this that I nerded out on the most is "ghosting" — technique used by @counterattack9 & co @stats_insights, among others.

Deep learning models predict how specific players — operating w/in specific setups — will move & execute actions. A paper here: https://t.co/9qrKvJ70EN

So many use-cases:
1/ Quickly & automatically spot situations where opponent's defence is abnormally vulnerable. Drill those to death in training.
2/ Swap target player B in for current player A, and simulate. How does target player strengthen/weaken team? In specific situations?

Advertisement

Pratham Prasoon
@PrasoonPratham

A simple guide on how to train your first neural network in under 10 minutes to kick-start your machine learning journey.

(+ no setup required and free extra resources)
🧵👇

For this exercise, you'll need :
- A computer/phone
- An internet connection
- Very basic Python knowledge
- Willingness to learn

What you do not need:
- Complex math
- An expensive computer
- A PhD

Math will come later on in your machine learning journey :)

(2 / 15)

Here's our problem,we are given data in which we are given the number of flats in a house and its corresponding price. Like a house with one flat is worth 10000, and 20000 for a house with 2 flats.

(3 / 15)

We can clearly tell that the price of the house increases by 10000 per extra flat however our computer does not know this and we won't it tell it about this, it'll have to figure things out on its own.

(4 / 15)

Here's the code👇

(5 / 15)

$Prashant \U0001f4da$

Prashant 📚
@capeandcode

Ever heard of Autoencoders?

The first time I saw a Neural Network with more output neurons than in the hidden layers, I couldn't figure how it would work?!

#DeepLearning #MachineLearning
Here's a little something about them: 🧵👇

Autoencoders are unsupervised neural networks whose architecture you can picture as two funnels connect from the narrow ends.

These networks are primary focus for compression tasks of data in Machine Learning.

We feed them the data so that they can learn the most important features, a smaller representation while keep the integrity of the data.

Later when someone needs, can just take that small representation and recreate the original, just like a zip file.📥

Being unsupervised, they require no labels.
Our inputs and outputs are same and a simple euclidean distance can be used as a loss function for measuring the reconstruction.

Of course, we wouldn't expect a perfect reconstruction.

We can think of an autoencoder having two components, encoder and decoder, represented by the below equations:

We are just trying to minimize the L here. All the backpropagation rules still hold.

Pratham Prasoon
@PrasoonPratham

There are several skills needed for learning machine learning that no one talks about.

Here are some of them.
(from what I've learned over the past two years)
🧵👇

This thread aims to introduce to you some of the skills often ignored for learning machine learning but are actually very important.

These skills will enable you to learn concepts quickly and more efficiently in this field.

(2 / 9)

1⃣ Reading

Probably one of the most underrated skills on this list.

In machine learning, you HAVE to read a lot of articles, papers, documentation, and whatnot.

It is mostly due to the theoretical nature of this field that reading is an important skill to have.

(3 / 9)

2⃣ Strong fundamentals in programming

Machine learning is just a lot of programming mixed with math and data.

Having clear programming fundamentals is crucial for this field.

I highly suggest you learn about these if you are using Python for machine learning.👇

(4 / 9)

- Object oriented programming in Python :Classes, Objects, Methods
- Lists & List functions
- Dunder Methods
- List comprehension
- List slicing
- String formatting
- List, Dictionaries & Tuples
- *args,**kwargs

(5 / 9)

You May Also Like

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.

libertyandjusticeforal...
@Mark923to25

1. #Qanon told us that Saudi Arabia is a central piece of the puzzle in taking out the Deep State...we are watching the Deep State attempt to remove Crown Prince MBS and disrupt Pres Trump's administration's ties with MBS and the "new" Saudi/US coalition. Early in his admin,

2....@Potus sent Jared Kushner (JK) to SA on an undisclosed trip and told King Salman that business as usual was over, and if he wanted Pres Trump's support, Prince Alwaleed would have to be divested of $ and power; Alwaleed is one of top Deep State $ men and was tied to HRC.

3. @Potus knew that before he could begin cleansing the US and the rest of the world of the DS, he would have to cut one of the financial head's off the snake (Alwaleed). After JK met w/ King Salman, Alwaleed was arrested and divested of billions; MBS became leader of SA.

4. SA loves Pres Trump because he's a man of his word; SA could not trust Hussein or Clintons because they use SA for oil and leverage; SA has many factions, but essentially you have the new and upcoming SA that is attempting to modernize through Crown Prince MBS, and then you

5...have the old guard represented by Alwaleed who was one of the Deep State financial heads and loyal to the DS more than SA; SA knew Hussein was financing Iran to hold western world hostage, and SA was caught in middle of Deep State black mail; this is why @Potus was celebrated

Advertisement

Nicolas Cole
@Nicolascole77

🚢 Atomic Essays Republishing Framework 🚢

1. Write Atomic Essay
2. Post image on Twitter
3. (Bonus) Copy/paste text as thread
4. Find relevant Question on Quora. Copy/paste Atomic Essay + image.
5. Copy/paste again on Medium.
6. Again on LinkedIn
7. Win

Guide below ✍️🚢👇

Step 1: Write Atomic Essay

I really enjoy writing right inside the Figma template. It helps give me a good sense of exactly how much "real estate" I have/have left before my time us up and I'm out of space.

Once finished, I export the image and send to my phone on Slack.

Step 2: Post image on Twitter

Before I publish my Atomic Essay on Twitter, I use the Edit/Photo Markup function on the iPhone to highlight standout sentences.

These are usually power-phrases: things the reader skims and thinks, "That's interesting," prompting them to read more.

Step 3: For the Ship 30 for 30 challenge, I only turn Atomic Essays into threads if...

1. The piece is SUPER actionable and lends itself well to the thread format (lots of bullets, quick points, lists, etc.)

or...

2. I'm referencing research and want to link to the pieces.

Step 4: Find relevant Question on Quora. Copy/paste Atomic Essay + image.

Search on Quora around the topic you wrote about. Find a related Question. Copy/paste the whole Atomic Essay as your "answer" (& fix formatting). Then include image so it appears in the thumbnail.

Andrew Chen
@andrewchen

1/ new essay: What's next for marketplace startups? Reinventing the $10 trillion service economy, that's what. Co-authored with @ljin18 https://t.co/fgKbrHTnH5. A short thread 👇

2/ Marketplace startups have done incredibly well over the first few decades of the internet, reinventing the way we shop for goods, but have been less successful services. It's bc services are complex, subjective, fragmented, and often in real life. Makes it hard

3/ There's been 4 major eras at making the service economy work online. The Listings Era, the unbundled Craiglist era, the Uber for X era, and the Managed Marketplace era

4/ Each era has added more value than the last, and utilized technology innovations, from internet to social / "read/write web" to mobile. The "Unbundling Craigslist" era was particularly epic at generating startup ideas

5/ The problem is, all the low-hanging fruit has been picked off. The techniques that got us to here won't get us to the next phase. So we have to do some pretty different things. That's why "Managed Marketplaces" have been a big deal - hire folks as W-2s, certify quality, etc.

$Corey Haines \U0001f4a1$

Corey Haines 💡...
@coreyhainesco

I think I'm giving up on mainstream marketing content.

I'm giving up on social media consumption too.

So little substance.

Need to devote more time doing. More time creating.

Who needs another "5 ways to boost growth" post? I click and am disappointed every time. Not again.

I don't want to poop on content marketing, but marketers need to step it up.

Or at least, founders need to know that doing something is not always better than doing nothing.

Why is content marketing not as effective as it used to be? An innumerable amount of factors...

But one things for damn sure.

Things have to change.

Two of the chief sins:
1. Unoriginal research/story/study/etc
2. Not having anything more to add that's meaningful

Why blog/podcast/vlog/etc about something that's already been said? Already been done?

Do we really need another interview with founder of x hot startup? Do we really need another ultimate guide about facebook ads?

Not all content is like this...

Sometimes, you get an occasional piece that truly leaves you better off than you were before. That doesn't make you want to skim.

An original case study. A first time interview with a founder. An honest account of an experiment. An explanation of a change, shift, or realization.