BC MACHINE LEARNING
Saved by @Alex1Powell

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

๐Ÿงต๐Ÿ‘‡

 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:

โ–ซ๏ธ Its rank
โ–ซ๏ธ Its shape
โ–ซ๏ธ Its data type

(3 / 16)
The rank of a tensor refers to the tensor's number of axes.

Examples:

โ–ซ๏ธ The rank of a matrix is 2 because it has two axes.
โ–ซ๏ธ 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:

โ–ซ๏ธ A square matrix may have (3, 3) dimensions.
โ–ซ๏ธ 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 ๐Ÿ's numpy library, here are some of the supported data types:

โ–ซ๏ธ float32
โ–ซ๏ธ float64
โ–ซ๏ธ uint8
โ–ซ๏ธ int32
โ–ซ๏ธ 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 โ€”or a 0D tensorโ€” 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 โ€”or a 1D tensorโ€” 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 โ€”or a 2D tensorโ€” 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:

โ–ซ๏ธ Vectors: 1D - (features)
โ–ซ๏ธ Sequences: 2D - (timesteps, features)
โ–ซ๏ธ Images: 3D - (height, width, channels)
โ–ซ๏ธ 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:

โ–ซ๏ธ (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:

โ–ซ๏ธ (samples, height, width, channels)

And a batch of videos as a 5D tensor:

โ–ซ๏ธ (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
My recommendation to start learning how to deal with structured data: Kaggle's Pandas Tutorial.

โ€ข Creating, Reading, Writing
โ€ข Indexing, Selecting, Assigning
โ€ข Summary Functions, Maps
โ€ข Grouping, Sorting
โ€ข Data Types, Missing Values
โ€ข Renaming, Combining

100% Python ๐Ÿ.
ALL
Santiago
Santiago
@svpino
A surprising situation.

A machine learning model predicting 3 classes ends up with these results:

โ€ข Class A: 90% accuracy
โ€ข Class B: 80% accuracy
โ€ข Class C: 70% accuracy

Class C seems to be the worst-performing.

But you know already that I'll say it isn't. โ†“

Here is the correct answer: We don't know yet which class is the worst.

This is important to understand, so keep reading.

Many people make this same mistake every day and try to fix things that ain't broken.

We are missing something, so let's go and get it.

How about if we ask a friend to look at the dataset manually?

Let's say these are the results of our friend doing the job:

โ€ข Class A: 95% accuracy
โ€ข Class B: 100% accuracy
โ€ข Class C: 71% accuracy

Do you see what just happened?

The model is actually really accurate when predicting Class C! 70% versus 71% when done by a human.

Class B, however, is a disaster: 80% versus 100% when done manually.

Class B seems to be the worse performing class!

The work that our friend did is called a "baseline."

Without having it, it's hard to determine how good are the results of a model.

I've seen tons of money down a drain just because teams didn't create a baseline beforehand.

But now, that won't happen to you ๐Ÿ˜‰.
ALL
Advertisement
Santiago
Santiago
@svpino
12 machine learning YouTube videos.

On libraries, algorithms, tools, and theory.

โ†“

1. Jupyter Notebooks: https://t.co/HqE9yt8TkB

2. Pandas: https://t.co/aOLh0dcGF5

3. Matplotlib: https://t.co/tKADpmihkh

4. Seaborn: https://t.co/s8EUxh6x1f


5. Numpy: https://t.co/pJoc0Lfjwm

6. Decision Trees: https://t.co/tKtUpO1K3l

7. Neural Networks: https://t.co/bc7emyjc9q

8. Scikit-Learn: https://t.co/LrKG7cMxRq


9. TensorFlow: https://t.co/fhO6T9sblU

10. PyTorch: https://t.co/5w9mJxijdd

11. Essense of Linear Algebra: https://t.co/o3kOnxl90i

12. Essense of Calculus: https://t.co/rfo7v0cpR4
ALL
Santiago
Santiago
@svpino
Interviews aren't only about technical skills.

Here are some questions to help you prepare.

๐Ÿงต๐Ÿ‘‡

Explain what you have been working on for the past few weeks.

What are the most exciting parts about that work?

What portion of it do you consider boring and why?

[2 / 10]

What specific libraries and frameworks are you familiar with?

What's the minimum set of libraries and frameworks that you'd recommend to any practitioner?

[3 / 10]

What kind of problems have you worked on in the past?

Can you list the specific use cases related to each one of these?

[4 / 10]

What is the most exciting project you have ever worked on?

What was your role and responsibilities on that project?

Why do you think your work on that project was important?

[5 / 10]
LIFE
Santiago
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 ๐Ÿž.

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:
โ€ข X โ†’ The input number
โ€ข y โ†’ The result (0 if even, 1 otherwise)
โ€ข f โ†’ 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 โ†’ 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:

โ€ข 2 โ†’ 0
โ€ข 5 โ†’ 1
โ€ข 8 โ†’ 0
โ€ข 4 โ†’ 0
โ€ข 3 โ†’ 1
โ€ข ...
ALL

More from Machine learning

Alejandro Piad Morffis
Alejandro Piad Morffis
@AlejandroPiad
This is a Twitter series on #FoundationsOfML.

โ“ Today, I want to start discussing the different types of Machine Learning flavors we can find.

This is a very high-level overview. In later threads, we'll dive deeper into each paradigm... ๐Ÿ‘‡๐Ÿงต

Last time we talked about how Machine Learning works.

Basically, it's about having some source of experience E for solving a given task T, that allows us to find a program P which is (hopefully) optimal w.r.t. some metric


According to the nature of that experience, we can define different formulations, or flavors, of the learning process.

A useful distinction is whether we have an explicit goal or desired output, which gives rise to the definitions of 1๏ธโƒฃ Supervised and 2๏ธโƒฃ Unsupervised Learning ๐Ÿ‘‡

1๏ธโƒฃ Supervised Learning

In this formulation, the experience E is a collection of input/output pairs, and the task T is defined as a function that produces the right output for any given input.

๐Ÿ‘‰ The underlying assumption is that there is some correlation (or, in general, a computable relation) between the structure of an input and its corresponding output and that it is possible to infer that function or mapping from a sufficiently large number of examples.
MACHINE LEARNING
Pratham Prasoon
Pratham Prasoon
@PrasoonPratham
Machine learning terms you must know about as a beginner.

๐Ÿงต๐Ÿ‘‡

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)
MACHINE LEARNING
Advertisement
Santiago
Santiago
@svpino
The 8-step quick-start guide to learn Machine Learning.

๐Ÿงต๐Ÿ‘‡

1โƒฃ Start with Python ๐Ÿ

Yes, you can do other languages, but Python is by far the most straightforward option.

๐Ÿ‘‡

2โƒฃ 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.)

๐Ÿ‘‡

3โƒฃ 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.

๐Ÿ‘‡

4โƒฃ Find a problem (already solved)

In my opinion, the best way to start is by working through a problem โ€”especially when you can learn from its solution.

Start with something simple. I usually recommend "Titanic" from Kaggle.

๐Ÿ‘‡
MACHINE LEARNING , STARTING MACHINE LEARNING
Fionna O'Leary, \U0001f56f\U0001f1ea\U0001f1fa
Fionna O'Leary, ๐Ÿ•ฏ๐Ÿ‡ช๐Ÿ‡บ...
@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


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?

Iโ€™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.


Hereโ€™s the link to the

Iโ€™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.
MACHINE LEARNING
Caio Rolla
Caio Rolla
@caio_rolla
Starting a new project using #Angular? Here is a list of all the stuff i use to launch my projects the fastest i can.

A THREAD ๐Ÿ‘‡

Have you heard about Monorepo? I created one with all my Angular (and Nest) projects using https://t.co/aY5llDtXg8.

I can share A LOT of code with it. Ex: Everytime i start a new project, i just need to import an Auth lib, that i created, and all Auth related stuff is set up.

Everyone in the Angular community knows about https://t.co/kDnunQZnxE. It's not the most beautiful component library out there, but it's good and easy to work with.

There's a bunch of state management solutions for Angular, but https://t.co/RJwpn74Qev is by far my favorite.

There's a lot of boilerplate, but you can solve this with the built-in schematics and/or with your own schematics

Are you not using custom schematics yet? Take a look at this:

https://t.co/iLrIaHVafm
https://t.co/3382Tn2k7C

You can automate all the boilerplate with hundreds of files associates with creating a new feature.
MACHINE LEARNING

You May Also Like

Simon DeDeo
Simon DeDeo
@SimonDeDeo
This is a pretty valiant attempt to defend the "Feminist Glaciology" article, which says conventional wisdom is wrong, and this is a solid piece of scholarship. I'll beg to differ, because I think Jeffery, here, is confusing scholarship with "saying things that seem right".


The article is, at heart, deeply weird, even essentialist. Here, for example, is the claim that proposing climate engineering is a "man" thing. Also a "man" thing: attempting to get distance from a topic, approaching it in a disinterested fashion.


Also a "man" thingโ€”physical courage. (I guess, not quite: physical courage "co-constitutes" masculinist glaciology along with nationalism and colonialism.)


There's criticism of a New York Times article that talks about glaciology adventures, which makes a similar point.


At the heart of this chunk is the claim that glaciology excludes women because of a narrative of scientific objectivity and physical adventure. This is a strong claim! It's not enough to say, hey, sure, sounds good. Is it true?
ALL
Angad Singh
Angad Singh
@Singh7575
๐™Ž๐™๐™–๐™ง๐™ž๐™ฃ๐™œ ๐™ข๐™ฎ ๐™ฌ๐™ž๐™จ๐™™๐™ค๐™ข ๐‘พ๐’๐’'๐’• ๐’ƒ๐’† ๐’”๐’–๐’“๐’‘๐’“๐’Š๐’”๐’†๐’… ๐’Š๐’‡ ๐’•๐’๐’Ž๐’๐’“๐’“๐’๐’˜ ๐’– ๐’“๐’†๐’‚๐’… ๐’•๐’‰๐’† ๐’”๐’‚๐’Ž๐’† ๐’”๐’•๐’–๐’‡๐’‡ ๐’Š๐’ 50๐’Œ ๐’˜๐’๐’“๐’Œ๐’”๐’‰๐’๐’‘ ๐’๐’“ ๐’”๐’๐’Ž๐’†๐’๐’๐’† ๐’Ž๐’‚๐’๐’‚๐’ˆ๐’Š๐’๐’ˆ ๐’š๐’๐’–๐’“ ๐’Ž๐’๐’๐’†๐’š ๐’˜๐’Š๐’•๐’‰ ๐’”๐’‚๐’Ž๐’† ๐’๐’๐’ˆ๐’Š๐’„
Simple and effective way 2 make Money


Idea 1:- Use pivot level like 14800 in case of nifty and sell 14800straddle monthly expiry (365+335) exit if nifty closes on daily basis below S1 or above R1

After closing below S1 if it closes above S1 next day or any day enter the same position again vice versa for R1

Idea2:- Use R1 and S1 corresponding strikes multiple
Incase of R1 15337 take 15300ce
N in case of S1 14221 use 14200pe
Sell both and hold till expiry or exit if nifty closes below S1 or above R1 around closing
If the same bounces above S1 and falls below R1 re-enfer same strikes

Use same criteria for nifty, usdinr and banknifty

(This is must)Use this margin rule for 1lot banknifty pair keep 4Lax margin
For nifty one lot keep 3Lax
For usdinr 100lots keep 4Lax

I bet you if you do this on consistent basis your ROI will be more than 70% on yearly basis.

Couldn't explain easier than this

Criticisms are most welcomed.
OPTIONSLEARNINGS , MONTHLY OPTIONS SELLING , OPTIONS LEARNING
Advertisement
dan spaceman
dan spaceman
@ohlaika
I'm gonna do my other star wars thread tomorrow, which will primarily be me yelling at a @RowanKaiser-shaped strawman for calling the First Order and The Resistance "cosplayers who the rest of the galaxy has to deal with"

the deal w/the New Republic, the First Order, and the Resistance is very weird and complex and I actually take issue with how Story Group frames the actual conflict.

pre-TFA stuff is presented as a "cold war" between the New Republic and the remnants of the Empire that form the First Order, which 100% makes sense.

But they frame the First Order's attack on the Hosnian system and the subsequent battle that takes place across TFA and TLJ as a full on war when it's very clearly a coup. A war implies at least equal standing, but the First Order completely wrecks shop and takes over the galaxy.

ok never mind I'm fucking doing this now.

The First Order fleet we see in TLJ is *not* the entire fleet of the First Order (I don't even think Starkiller Base was their main base of operations honestly, it couldn't have been considering they were operating out of Wild Space)
CULTURE
Loren Brichter
Loren Brichter
@lorenb
So it turns out that Google Chrome was making everything on my computer slow *even when it wasnโ€™t running*, because it installs something called Keystone which is basically malware.

I made a website because this shouldnโ€™t

Wired first reported on how bad Keystone was 11 years ago when they put it into Google Earth (they seem to put it in all their popular

The fact that Keystone hides itself in Activity Monitor is bizarre. (The only sign of it was excessive CPU usage of WindowServer which is a system process).

I donโ€™t know if Google was doing something nefarious with Keystone, or a third party figured out how to (which Wired warned about). But either way, Iโ€™m not inclined to give Google-the-organization the benefit of the doubt (despite the many good people who work on Chrome)...

...since it's been a decade+ and this still hasn't been "fixed".

There is no reason for auto-update software to need to do what Chrome/Keystone was doing. It also has a long history of crashing Macs.
TECH
Billy Bostickson \U0001f3f4\U0001f441&\U0001f441 \U0001f193
Billy Bostickson ๐Ÿด๐Ÿ‘&๐Ÿ‘ ...
@BillyBostickson
1. Project 1742 (EcoHealth/DTRA)
Risks of bat-borne zoonotic diseases in Western Asia

Duration: 24/10/2018-23 /10/2019

Funding: $71,500
@dgaytandzhieva
https://t.co/680CdD8uug


2. Bat Virus Database
Access to the database is limited only to those scientists participating in our โ€˜Bats and Coronavirusesโ€™ project
Our intention is to eventually open up this database to the larger scientific community
https://t.co/mPn7b9HM48


3. EcoHealth Alliance & DTRA Asking for Trouble
One Health research project focused on characterizing bat diversity, bat coronavirus diversity and the risk of bat-borne zoonotic disease emergence in the region.
https://t.co/u6aUeWBGEN


4. Phelps, Olival, Epstein, Karesh - EcoHealth/DTRA


5, Methods and Expected Outcomes
(Unexpected Outcome = New Coronavirus Pandemic)
ALL