BC MACHINE LEARNING

Saved by @Mollyycolllinss

Pratham Prasoon
@PrasoonPratham 5 years, 5 months ago 894 views

Save to PDF Share See On Twitter

Machine learning terms you must know about as a beginner.

🧵👇

These terms won't mean anything unless you know what Machine learning is all about.

> Machine learning is the process of making a program which allows a computer to learn from data.

The data could be anything, images, audio or even text.

(2 / 11)

In machine learning we use something called a neural network, this is essentially an imitation of the human brain.

> Neural Networks are a digital imitation of the neurons you see in the human brain.

(3 / 11)

In these neural networks, data flows through them and each neuron (the circle) has a numerical value which will change.

> The value of a neuron gets changes to something which is close to what we want each time the data passes through the neural network.

(4 / 11)

Think of the neurons as dials on a lock, you have to tune every dial to open the lock.

It is almost impossible for a human to tune thousands of dials like these, but a computer certainly can.

(5 / 11)

Once the dials are well tuned, you have a well trained neural network!

Each dial's numeric value is dependent on a "weight" and a "bias". The weight determines how important the neuron is and the bias make it flexible.

(6 / 11)

So here's a recap of what we've looked at so far:

The neural net is the brain of the machine learning model, the dials you have to adjust to make that neural net work are the neurons.

(7 / 11)

Each time data passes through the neural network, we get to know how wrong it is. The measure of how wrong a neural network is called the "loss". The neural network uses this thing called an "optmizer" to reduce "loss" and tries to get less wrong after each iteration.

(8 / 11)

The number of times the data passes through the neural net is called the "epoch".

Let's summarize the entire thing👇

(9 / 11)

Neural Network: The brain of our machine learning model
Neuron : Each dial in a neural network
Weight : How important the neuron is
Bias : Flexibility of neuron

(10 / 11)

Epoch : Number of times the data passes through the neural network
Loss : How wrong the neural net is
Optimizer : Tries to reduce loss and make the neural net less wrong

Congrats! You know a fair bit about commonly used machine learning terms 😉
(11 / 11 🎉)

More from Pratham Prasoon

Pratham
@PrasoonPratham

This is a beginner's guide on mining cryptocurrencies.

🧵 👇🏻

Mining 101

Typically, when you transfer money using a service like Paypal, they take a small cut for facilitating the exchange.

In cryptocurrencies, people like you and me act as Paypal and facilitate exchanges of cryptocurrency. We get a cut for this just like Paypal did.

In order to make these transactions happen, our computers need to do some calculations which requires a lot of computational power.

A GPU or a Graphics Processing Unit which is typically marketed for gaming workloads can be used to mine cryptocurrencies.

Why do you need a GPU?

Today, there are so many miners that the "difficulty" of mining cryptocurrencies has skyrocketed, which basically means it takes a lot of computational power to mine crypto which GPUs can provide and CPUs cannot.

(❗ This is an oversimplification)

If you are interested in the inner workings of how blockchain and cryptocurrency, then I highly suggest that you read this thread by @oliverjumpertz

What actually is a Blockchain?

Bitcoin is breaking record after record, but there must be more to the technology than just crypto, or not? Well, we can take a look at the underlying technology first to understand what it actually provides to us.

\U0001f9f5\u2b07\ufe0f
— Oliver Jumpertz (@oliverjumpertz) February 16, 2021

Pratham
@PrasoonPratham

Everyone tells you how important math is in machine learning.

But I believe that if you want to learn machine learning today, there are things more important than math which very few people will tell you about.

Here are 5 of them.

🧵 👇🏻

The field of machine learning has been very academic which is why there is so much emphasis on learning math for it.

But, today with the frameworks that we have, not knowing how to multiply matrices is far less of an issue than knowing how to use the tools in this list 👇🏻

Yes, I know; you have R, Julia, and whatnot for machine learning but as of today, Python is the industry standard.

Get your data structures and algorithms right in Python because you will need them, here are some concepts worth learning 👇🏻

Let's say you're building the next big GPT-3 powered app that's going to take over the world.

You add a new feature to your app but it breaks the entire thing, what do you do now?

Learn Git, the ultimate version control tool.

I use this cheat sheet for all my git needs 👇🏻

You will be constantly be working on multiple packages which specific python version requirements 🐍

Virtual environments like Anaconda or Poetry will make this process much easier for you.

Who likes to see broken dependencies while running code?

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)

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)

Pratham
@PrasoonPratham

A list of my favourite tutorials for learning Python as a beginner.

🧵 👇🏻

All the tutorials below include the basics like installation, variables etc.

I've also listed out the key highlights of each tutorial so that it is easy for you decide which one to pick.

Before going through these tutorials I would highly suggest you to go through this thread if you are a complete

Are you planning to learn Python for machine learning this year?

Here's everything you need to get started.
\U0001f9f5\U0001f447
— Pratham (@PrasoonPratham) February 13, 2021

The Full Python Course from learn with Python with Rune

key highlights
- 17 part course
- Jupyter notebooks
- Free eBook included

Duration: 8

The Python Beginner's course on FreeCodeCamp's YouTube Channel.

Key highlights

- Building a casic calculator
- Mad Libs Game
- Slightly advanced concepts like inheritance, Classes etc.

Duration: 4

More from Machine learning

Quant@Python
@BeingHorizontal

Thread for beginners; How to learn machine learning.

Let’s start with something really simple and useful not just for Machine Learning.

Start with a Python library called pandas. It’s a huge library but it's mostly fun for traders because it's kind of rewarding to learn each function and how it gonna affect the way you handle the financial data.

Then learn some basic stuff about Python library called NumPy. Pandas is built on NumPy. Numpy is huge, you just need to understand some basic NumPy functions like NumPy shapes and NumPy arrays

If you understand pandas then you will understand NumPy arrays and shapes easily. Side note: Numpy shapes gonna play an important part in the deep learning model called LSTM - mainly used for time-series analysis(such as financial data) and Natural Language Processing (NLP)

$Fionna O'Leary, \U0001f56f\U0001f1ea\U0001f1fa$

Fionna O'Leary, 🕯🇪🇺...
@fascinatorfun

Thanks for this incredibly helpful analysis @dgurdasani1

Two questions. 1/ Does this summarise the AZ published data :
The plan is to extend the time interval for all age groups despite it being largely untested on the over 55yrs, although the full data is not yet published

SUMMARY: the Oxford/Astra trial examined dosing with gaps between 4-12 wks- although longer gaps appear to be limited mostly to younger participants. There was no difference reported in published data between these & efficacy from the 1st dose seems high for severe disease.
— Deepti Gurdasani (@dgurdasani1) December 31, 2020

Do we have the actual numbers of over 55yr olds given a 2nd dose at c12 weeks and the accompanying efficacy data?

Not to mention the efficacy data of the full first dose over that same period?

I’d quite like to know whether I am to be a guinea pig & the ongoing risks to manage

You attached photos of excerpts from a paper. Could you attach the link?

Re Pfizer. As I understand it the most efficacious interval for dosing was investigated at the start of the trial.

Discussions of 1 vs 2 doses suggest many are not aware of Pfizer's trials which evaluated 1 vs 2 dose immunogenicity, assessed multiple formulations (BNT162b1 BNT162b2 etc) & conducted dose-ranging in both young & old adults at the start. Saw "clear benefit of booster at day 21" pic.twitter.com/mpyxu9xFSF
— Dr Nicole E Basta (@IDEpiPhD) December 31, 2020

Here’s the link to the

I’ve got to say that this way of making and announcing decisions is not inspiring confidence in me and I am very pro vaccination as a matter of principle, not least because my brother caught polio before vaccinations available.

Advertisement

Santiago
@svpino

11 key concepts of Machine Learning.

— Supervised Learning Edition —

🧵👇

😜

Before starting, remember that, if you follow me, one of your enemies will be immediately destroyed (and you'll get to read more of these threads, of course.)

And if you don't follow me, well, you just hurt my feelings.

😜

1. Labels

(Also referred to as "y")

The label is the piece of information that we are predicting.

For example:

- the animal that's shown in a picture
- the price of a house
- whether a message is spam or not

👇

2. Features

(Also referred to as "x")

These are the input variables to our problem. We use these features to predict the "label."

For example:

- pixels of a picture
- number of bedrooms of a house
- square footage of a house

👇

3. Samples

(This is also known as "examples.")

A sample is a particular instance of data (features or "x.") It could be "labeled" or "unlabeled."

👇

Marcus Mengs
@mame82

Okay, doing my first baby steps with r2frida (which combines the power of @radareorg and @fridadotre).

Gonna share my progress in this thread (live, so keep calm).

The goal: Runtime inspection of data sent out by TikTok !!before!! it gets encrypted

1/many

First of all, we do not start from zero. I got some prior knowledge from past reversing attempts and want to share some important facts.

TikTok's (log data) encryption is accomplished by a native library. The Android Java code just serves as proxy function to the native function

The decompiled code for the respective native JNI function of an older TikTok version looks something like this, but in this example I use the most current TT version (no statical analysis done, yet)

In case you never reversed native libraries which were build to interface with Android Java layer via JNI, I highly suggest the entry level introduction on the topic by @maddiestone

Before we start, I want to pinpoint some important aspects (which are also covered by Maddie's videos).

1) Unlike raw C-functions, JNI functions like the one showcased above, receive pointers to complex Java objects .

F.e. a function receiving a String on the Java layer...

Pratham Prasoon
@PrasoonPratham

Here's what you'll hear when you first get into machine learning.

- Neural networks
- Loss
- Weights
- Biases
- Epochs
- Neurons
- Optimizers
...

It can get very confusing really fast!

Here are some of the terms you should know about.
(I wish I had this before)

🧵👇

These terms won't mean anything unless you know what Machine learning is all about.

> Machine learning is the process of making a program which allows a computer to learn from data.

The data could be anything, images, audio or even text.

In machine learning we use something called a neural network, this is essentially an imitation of the human brain.

> Neural Networks are a digital imitation of the neurons you see in the human brain.

In these neural networks, data flows through them and each neuron (the circle) has a numerical value which will change.

> The value of a neuron gets changes to something which is close to what we want each time the data passes through the neural network.

Think of the neurons as dials on a lock, you have to tune every dial to open the lock.

It is almost impossible for a human to tune thousands of dials like these, but a computer certainly can.

You May Also Like

Vibhu Vashisth
@VIBHU_Tweet

THE MEANING, SIGNIFICANCE AND HISTORY OF SWASTIK

The Swastik is a geometrical figure and an ancient religious icon. Swastik has been Sanatan Dharma’s symbol of auspiciousness – mangalya since time immemorial.

The name swastika comes from Sanskrit (Devanagari: स्वस्तिक, pronounced: swastik) &denotes “conducive to wellbeing or auspicious”.
The word Swastik has a definite etymological origin in Sanskrit. It is derived from the roots su – meaning “well or auspicious” & as meaning “being”.

"सु अस्ति येन तत स्वस्तिकं"
Swastik is de symbol through which everything auspicios occurs

Scholars believe word’s origin in Vedas,known as Swasti mantra;

"🕉स्वस्ति ना इन्द्रो वृधश्रवाहा
स्वस्ति ना पूषा विश्ववेदाहा
स्वस्तिनास्तरक्ष्यो अरिश्तनेमिही
स्वस्तिनो बृहस्पतिर्दधातु"

It translates to," O famed Indra, redeem us. O Pusha, the beholder of all knowledge, redeem us. Redeem us O Garudji, of limitless speed and O Bruhaspati, redeem us".

SWASTIK’s COSMIC ORIGIN

The Swastika represents the living creation in the whole Cosmos.

Hindu astronomers divide the ecliptic circle of cosmos in 27 divisions called https://t.co/sLeuV1R2eQ this manner a cross forms in 4 directions in the celestial sky. At centre of this cross is Dhruva(Polestar). In a line from Dhruva, the stars known as Saptarishi can be observed.

$\u0939\u0920\u092f\u094b\u0917\u0940$

हठयोगी...
@hathyogi31

#3/thread on Angkor wat

Christianity and islam may be the largest religion of today’s world but Sanatan dharm has the largest religious monument in the world in the form of Angkor wat. It is situated in combodia and spread across over 400 acres / 1.6 km².

It was listed as a UNESCO World Heritage Site in 1992, which encouraged an international effort to save the complex.
It was originally built as a Hindu temple dedicated to the god Vishnu. In Khmer, the Cambodian language, Angkor means "city" and Wat means "temple grounds".

So Angkor Wat means "Temple City". Its original name was Vrah Vishnuloka or Parama Vishnuloka, meaning the sacred dwelling of Vishnu in Sanskrit.
But, it gradually turned into a Buddhist temple towards the end of the 12th century & is still used for worship today.

Angkor Wat was initially designed and constructed in the first half of the 12th century, during the reign of Suryavarman II, as the king’s state temple and capital city. It was built without the aid of any machinery, as there was no machinery available at that time.

Evidence for these dates comes in part from inscriptions, which are vague, but also from the architectural design and artistic style of the temple and its associated sculptures.

Another aspect is that the five central towers of Angkor Wat symbolize the peaks of Mount Meru,

Advertisement

Suhas S. Hardutt
@HarduttSuhas

THE BATTLE OF TALIKOTA and the destruction of Vijaynagar (Hampi)
26 January 1565

A tale of valor, deception and decimation.

A grim reminder that if we fail to protect our heritage, it will eventually crumble under the onslaught of "forces of anarchy".
(Elaborate thread)

This decisive battle was fought between the Vijayanagara empire and the Deccan sultanates resulting in a rout of Vijayanagara and ending the last major medieval era Hindu kingdom in south India.(1)

The seeds of 1565 encounter were sown more than 250 years earlier when the forces of the Delhi Sultanate, during the time of Alauddin Khilji and later Md Bin Tughlaq swept through southern India in an expansion spree.(2)

By middle of the 14th century, facing rebellions, Tughlaq withdrew to Delhi, leaving behind 2 empires, Bahmani, which ruled the Deccan from Kalaburagi, and Vijayanagara, which ruled most south India with its capital at Vijayanagar.(3)

The Raichur Doab, between the Krishna and Tungabhadra rivers, existed as a natural boundary between these two kingdoms, with wars often breaking out over control of this territory.(4)

Learning @ Prakash
@Prakashplutus

My simple Approach towards Breakout trading :

1. Scan stocks on the basis of FTDB Scanner.

2. Buy stocks with EMA-9> EMA-21> EMA-63 > EMA 200 & Volume 200% up

3. maximum SL of 1.25X ( ATR )

4. I do breakout trading only in Nifty -500 stocks

#StockMarket
#trading
#Nifty

$Antonio Garc\xeda Mart\xednez$

Antonio García Martíne...
@antoniogm

Observing the public conversation around FB, and the private ones happening among techies and ex-FBers, I think the mutual misunderstanding is worse than when I set out two years (and 500 pages) ago to (in a small way) bridge that gulf.

We're basically fucked.

The tech world has gotten so huge, self-reinforcing, and insulated from reality they can no longer even vaguely look at themselves (and their actions) as others do. They just live on a different planet than most people.

Conversely, the average tech consumer doesn't understand the technology that has slowly taken over their lives, and their designated emissaries to figure it out--politicians, pundits, regulators, journalists--understand it barely better than they do, and have their own agendas.

To say more than generalities for a moment, here's what I think is likely the core problem.

Techies take weird, improbable visions, and make them realities: some BS pitch deck to a VC, mixed with money and people, really does turn into some novel thing.

Most people work inside a legacy industry that's evolved that way over time (usually for good reasons), and they think about the future via some analogy with their present (which is a function of a long-ago past). The interruption that tech will introduce is often hard to grasp.