BC MACHINE LEARNING
Saved by @Alex1Powell

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 data type of a tensor refers to the type of data contained in it.

For example, when thinking about Python 🐍's numpy library, here are some of the supported data types:

▫️ float32
▫️ float64
▫️ uint8
▫️ int32
▫️ int64

(6 / 16)
In the previous tweets I used the terms "vector" and "matrix," to referr to tensors with a specific rank (1 and 2 respectively.)

We can also use these mathematical concepts when describing tensors.

(7 / 16)
A scalar —or a 0D tensor— has rank 0 and contains a single number. These are also called "0-dimensional tensors."

The attached image shows how to construct a 0D tensor using numpy. Notice its shape and its rank (.ndim attribute.)

(8 / 16)
A vector —or a 1D tensor— has rank 1 and represents an array of numbers.

The attached image shows a vector with shape (4, ). Notice how its rank (.ndim attribute) is 1.

(9 / 16)
A matrix —or a 2D tensor— has rank 2 and represents an array of vectors. The two axes of a matrix are usually referred to as "rows" and "columns."

The attached image shows a matrix with shape (3, 4).

(10 / 16)
You can obtain higher-dimensional tensors (3D, 4D, etc.) by packing lower-dimensional tensors in an array.

For example, packing a 2D tensor in an array gives us a 3D tensor. Packing this one in another array gives us a 4D tensor, and so on.

(11 / 16)
Here are some common tensor representations:

▫️ Vectors: 1D - (features)
▫️ Sequences: 2D - (timesteps, features)
▫️ Images: 3D - (height, width, channels)
▫️ Videos: 4D - (frames, height, width, channels)

(12 / 16)
Commonly, machine learning algorithms deal with a subset of data at a time (called "batches.")

When using a batch of data, the tensor's first axis is reserved for the size of the batch (number of samples.)

(13 / 16)
For example, if your handling 2D tensors (matrices), a batch of them will have a total of 3 dimensions:

▫️ (samples, rows, columns)

Notice how the first axis is the number of matrices that we have in our batch.

(14 / 16)
Following the same logic, a batch of images can be represented as a 4D tensor:

▫️ (samples, height, width, channels)

And a batch of videos as a 5D tensor:

▫️ (samples, frames, height, width, channels)

(15 / 16)
If all of this makes sense, you are on your way! If something doesn't click, reply with your question, and I'll try to answer.

Either way, make sure to follow me for more machine learning content! 2021 is going to be great!

(16 / 16)

More from Santiago

Santiago
Santiago
@svpino
Here is a simple example of a machine learning model.

I put it together a long time ago, and it was very helpful! I sliced it apart a thousand times until things started to make sense.

It's TensorFlow and Keras.

If you are starting out, this may be a good puzzle to solve.


The goal of this model is to learn to multiply one-digit
TECH
Santiago
Santiago
@svpino
10 machine learning questions you should be able to answer.

I started experimenting with a questionnaire before interviewing candidates. Applicants submit a video or written answers to apply for the position.

Thread: Let's look at 10 of these questions.

The questionnaire solves a couple of problems:

1. Weeds out candidates that aren't ready for the job.

2. It significantly cuts down the time we spend talking synchronously.

One problem: It requires extra time from the candidate before the phone interview.

Here are some numbers on a job posting before using the questionnaire:

• 249 applicants
• 13 good applications

That's only 5%.

This sucks.

Numbers after using the questionnaire:

• 44 applicants
• 21 good applications

That's 47%.

This is much better.

I look at it this way:

Sooner or later, I'll ask these questions, and the candidate will have to answer them.

I'd rather give them space and the opportunity to think about their answers without any pressure.

Those who can't or don't want to answer won't apply. That's fine.
DS
Advertisement
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
ALL
Santiago
Santiago
@svpino
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 😉.
ALL
Santiago
Santiago
@svpino
I learned enough AI/ML in 12 months to change my life forever.

You can do the same, and it all starts with a killer process to learn new things.

You can steal my approach. Every detail on the latest issue of my newsletter: https://t.co/9gaenLByFb.

Make it work for you.
ALL

More from Machine learning

Cory Doctorow #BLM
Cory Doctorow #BLM
@doctorow
We hear a lot about Facebook as a platform for manipulation - using machine learning to bypass our critical faculties and trick us into believing things that are bad for us - but the real show is in Facebook's ability to target, not manipulate.

1/


People who hold disfavored views struggle to find one another and mobilize. To find other people that feel the same way as you and make common cause with them to effect political change, you have to reveal your views and suffer social sanction.

2/

Search allows people who hold these views to find one another. If you have a deep feeling about your gender being nonbinary but don't know the words for it, you can search for communities of people who have those words, join them, and discover who you've been all along.

3/

This is why, in this moment, so many ideas are migrating from the fringe to the center: ideas about racial justice, gender identity, alternatives to market systems, etc. People have harbored these views all along, but have held back on expressing them.

4/

Being able to express yourself in private, among people who share your views, is a prelude to going public and putting your case to the wider world in hopes of effecting change.

5/
MACHINE LEARNING
Pratham Prasoon \U0001f680
Pratham Prasoon 🚀...
@PrasoonPratham
Here's how I got started with my first machine learning project and you can too.
Let's take a look.

(This thread will take from zero to being a hero in machine learning, trust me)

(1 / 22)
🧵👇


Getting started with your first machine learning project might actually much easier than it seems, if I can do it, certainly anyone can.

I did not use:
- Any Math
- An expensive computer
- Complex programming concepts

(2 / 22)

Here's what I did use:

- A free GPU on Google Colab
- Python
- TensorFlow
- Numpy
- Pandas
- Kaggle
- Scikit-Learn
- Google
- StackOverFlow

(3 / 22)

This project was actually a Kaggle challenge based on the MNIST dataset which is a collection images of 70,000 hand written digits.

You can find the dataset here👇
🔗//kaggle.com/c/digit-recognizer

(4 / 22)


Before we go over the code of this project, it is highly reccomended that you complete this free course on YouTube👇

Machine Learning foundations course
🔗//youtu.be/_Z9TRANg4c0

Code👇
🔗//colab.research.google.com/github/PrasoonPratham/Kaggle/blob/main/MNIST.ipynb

(5 / 22)
MACHINE LEARNING
Advertisement
Pratham Prasoon
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
MACHINE LEARNING
Anson Horton
Anson Horton
@AnsonHorton
1/ It's probably not the first thing you think of, but when we started .NET (COM+) in the late 90s, C# didn't exist yet. We were working on it at the same time as the CLR and the framework. So, you might wonder, what language was being used to generate IL and write the BCL?

2/ The answer is a language that we called SMC that Peter Kukol wrote the compiler for. Peter is a flat out amazing engineer and wrote the core parts of the compiler in just a few days. This unblocked the framework team, allowed vetting the runtime and interpreter, etc.

3/ SMC was a trimmed down C++ variant and the compiler was written in itself (i.e. SMC). It didn't support things like destructors, multiple inheritance, virtual base classes, etc. But, overall it enabled progress that would have otherwise been stalled.

4/ It did introduce a problem for the C# language and compiler team though. Every day more and more code was written in SMC, a language that we did not intend to ship externally. Designing a new language is hard (well, at least, a general purpose one that becomes popular).

5/ So there was a constant balancing act between laying enough of the foundation of the language and the C# compiler to replace SMC and making sure that the design lived up to the goals and ideals the team was striving for. If we waited too long to adopt C#,
MACHINE LEARNING
Roger Grosse
Roger Grosse
@RogerGrosse
Important paper from Google on large batch optimization. They do impressively careful experiments measuring # iterations needed to achieve target validation error at various batch sizes. The main "surprise" is the lack of surprises. [thread]

https://t.co/7QIx5CFdfJ


The paper is a good example of lots of elements of good experimental design. They validate their metric by showing lots of variants give consistent results. They tune hyperparamters separately for each condition, check that optimum isn't at the endpoints, and measure sensitivity.

They have separate experiments where the hold fixed # iterations and # epochs, which (as they explain) measure very different things. They avoid confounds, such as batch norm's artificial dependence between batch size and regularization strength.

When the experiments are done carefully enough, the results are remarkably consistent between different datasets and architectures. Qualitatively, MNIST behaves just like ImageNet.

Importantly, they don't find any evidence for a "sharp/flat optima" effect whereby better optimization leads to worse final results. They have a good discussion of experimental artifacts/confounds in past papers where such effects were reported.
MACHINE LEARNING

You May Also Like

foone
foone
@Foone
So I was talking to @gewt about Job: A Comedy of Justice and I came up with a theory that I think explains why Heinlein's late-period work is so kinda-terrible and why I still enjoy it so much


So Heinlein had always been very interesting in the short parts of his novels, like the little snippets inside chapters. He had a very fun writing style, and wrote some fun dialogue with fun characters, right?>
It probably comes from how much of his early stuff was short fiction

And I think what happened with a lot of his longer works is that he'd just start writing fun bits and hope it would end up going somewhere or having a bigger plot by the end. like eventually he'd figure out where this was going, then go back and rewrite it into a cohesive whole

and I'm sure he had editors that'd help this process. No editor would let you publish something as rambly and changing-gears-every-other-chapter as The Number Of The Beast, for example... unless you were God-King Of Science Fiction 1980s Robert Heinlein.

so basically I think what happened is that by the 80s (when he was in his seventies!!) he lost the drive to go back and rewrite and he was too Untouchable for editors to make him.
CULTURE
Novid Houellebecq (That's Hollaback)
Novid Houellebecq (Tha...
@GarouGothic
Ok, here is a thread for you.
What happens when you have:
Netflix
Apple
Amazon
WarnerMedia +
Disney+
SonyCrackle (Reboot)
Verizon All Access (after they buy CBS/Viacom)
UniversalSkyMedia
By 2021
Answer? Internet Slows To A Craw and Dies.
Why?
Bandwidth.

Netflix's gets 35% of all internet traffic.
Now we all know Apple Coming to Netflix Corner.
We know that WarnerMedia Planning One
We Know about Disney+
Now how will the net handle 8 Streaming Platforms all at once?
Answer - IT CANT.

But Novid, the speed, the 4K the all everything?
NOOOOO BUDDY.
Even if you could do it and even if AWS ran six million clouds, The Net Will still slow to a crawl. 35%, goes to nearly 90% if any of the 8 or all of the 8 eat at netflix's numbers.

Oh, they wouldn't be running at once.
FOOL. You forget how bad things were when game of thrones season premieres came around. HBO SERVERS FALL DOWN GO BOOM!

Now see if a season like 2021 come around and they air shows on a same day. It gets crazy. AT&T and others gonna realize they cant build out forever. Something will give and it might be your entertainment consumption big time.
TECH
Advertisement
Marc K\xf6hlbrugge
Marc Köhlbrugge
@marckohlbrugge
💬 I often get Q’s like these:

How did you get your first customers for WIP? How did you grow BetaList’s traffic? Etc.

Makers are looking to reverse-engineer success. I see it everywhere.

I don’t think it works that way and the answers to those questions are mostly useless. 💥

I have built dozens of different products over the last couple of years. The vast majority failed. 😭

Surely if I know the answers to these questions, but still fail over and over again, these answers aren’t that useful. 🤷‍♀️

So what’s a better question to ask? 🤔

99.9% of the questions I receive are about the products that did well. In a way that makes sense, because we quickly forget about those that didn’t succeed.

🧠 This is known as survivorship bias.

Focusing on what survived, while ignoring what made it survive in the first place.

The real question, what you really want to know, is this:

What makes @WIP, @BetaList, and to some extent @AllStartupJobs succeed where my countless other attempts failed?

What separates a failed product 👎 from a successful product 👍?

Honestly, I don’t know. I wish I did.

It’s like Steve Jobs said “I’ll know it when I see it.” 👀

Same is true when we make products. We don’t know upfront what will work. But once we see an inkling of a product that does have potential, it’s not that hard to spot.
STARTUPS
Nikita Poojary
Nikita Poojary
@niki_poojary
Time for a Thread🧵On yesterday’s “F&O Pe Charcha - Diary Of An Option Seller” with @Mitesh_Engr by @Paytm Money

Why Gain/loss ratio is important that the batting average
• More than the Win Loss ratio check the total Gain /loss ratio
• If your avg loss is 1% and avg gain is +5% then even if you are losing in 7 positions and winning in 3 out of 10 still you will be net profitable

Treat Trading as a business:
• Stick to a single strategy. Eg: A restaurateur usually wouldn’t be changing his recipe on a daily basis
• Mitesh Sir only works on BO or BD strategy, as he is a versatile trader

• Any trader should atleast experience 3 scenarios i.e. bull, bear & consolidation
• Target 4% per month i.e. 48% p.a.
• Option buying requires skill, everyday there wont be huge momentum, so buying options won’t yield good results, but high chances of falling into a bad habit

Stock Selection:
• In F&O segment there are ~150 stocks
• Not everyday all stocks will move
• Only 5-7 stocks move upside or downside
• Focus only these momentum stocks
• Check which one is moving
• Range BO/BD never disappoints. BO/BD from a rectangle (consolidation)
MPLEARNINGS , ALL , OPTION SELLING
Vibhu Vashisth
Vibhu Vashisth
@VIBHU_Tweet
AGAMA SHASTRA:THE SCIENCE BEHIND THE MARVELS OF HINDU ARCHITECTURE

Agama Shastra is a Sanskrit word that means the manual for worship, temple building, rituals etc in Hindu Tradition.From Sanskrit,agama means handed down by tradition and Shastra means a commentary or treatise.


Therefore, Agama Shastra is a collection of ideas that drafts the rules for worship, temple construction, spirituality and rituals. It has been a guideline for many Hindus from ancient times. It's a collection of Sanskrit, Tamil and Grantha scriptures that mostly contains...


...methods of temple construction, idol creation, philosophical doctrines and meditative practices. It came into being after years of assimiliation and from a variety of sources. Some parts of it are pre-vedic while some are post-vedic.


Hindu Temples are not just temples, they are the pride and identity of Hindus. They are the symbols of Hindu unity and their religious aspirations. Temples are the places of spiritual healing and are our connection with the creator almighty.


Temples are the priceless treasure of our History, Heritage ,Art & Architecture. Architecture that mesmerises and spell bounds you. And Agama Shastra is that very text which is responsible for such a mesmerising and spell binding quality and beauty of our Hindu Temples.
ALL