BC MACHINE LEARNING
Saved by @Alex1Powell

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."

👇
4. Labeled sample

Labeled samples are used to train and validate the model. These are usually represented as (x, y), where "x" is a vector containing all the features, and "y" is the corresponding label.

For example, a labeled sample could be:

([3, 2, 1500], 350000)
5. Unlabeled sample

Unlabeled samples contain features, but they don't contain the label: (x, ?)

We usually use a model to predict the labels of unlabeled samples.

👇
6. Model

A model defines the relationship between features and the label.

You can think of a model as a set of rules that, given certain features, determines the corresponding label.

For example, given the # of bedrooms, bathrooms, and square footage, we get the price.

👇
7. Training

Training is a process that builds a model.

We show the model labeled samples during training and allow the model to gradually learn the relationships between features and the label.

👇
8. Validation

Validation is the process that lets us know whether a model is any good.

Usually, we run a set of (unseen) labeled samples through a model to ensure that it can predict the labels.

👇
9. Inference

Inference is the process of applying a trained model to unlabeled samples to obtain the corresponding labels.

In other words, "inference" is the process of making predictions using a model.

👇
10. Regression

A regression model predicts continuous values, for example:

- the value of a house
- the price of a stock
- tomorrow's temperature

👇
11. Classification

A classification model predicts discrete values, for example:

- the picture is showing a dog or a cat
- the message is spam or not
- the forecast is sunny or overcast

More from Santiago

Santiago
Santiago
@svpino
20 machine learning questions that will make you think.

(Cool questions. Not the regular, introductory stuff that you find everywhere.)

🧵👇

1. Why is it important to introduce non-linearities in a neural network?

2. What are the differences between a multi-class classification problem and a multi-label classification problem?

3. Why does the use of Dropout work as a regularizer?

👇

4. Why you shouldn't use a softmax output activation function in a multi-label classification problem when using a one-hot-encoded target?

5. Does the use of Dropout in your model slow down or speed up the training process? Why?

👇

6. In a Linear or Logistic Regression problem, do all Gradient Descent algorithms lead to the same model, provided you let them run long enough?

7. Explain the difference between Batch Gradient Descent, Stochastic Gradient Descent, and Mini-batch Gradient Descent.

👇

8. What are the advantages of Convolution Neural Networks (CNN) over a fully connected network for image classification?

9. What are the advantages of Recurrent Neural Networks (RNN) over a fully connected network when working with text data?

👇
ALL , MACHINE LEARNING
Santiago
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.
DS
Advertisement
Santiago
Santiago
@svpino
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.

👇
MACHINE LEARNING , STARTING MACHINE LEARNING
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
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

More from Machine learning

IM POCUS Focus
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/
MACHINE LEARNING
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


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.


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.
MACHINE LEARNING
Advertisement
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
Cassie Kozyrkov
Cassie Kozyrkov
@quaesita
1/🧵 Good #DataScience advice that breaks pretty much every rule you learned in class... a thread. (+full blog post linked)

English version: https://t.co/dG4l6vPFBT
Spanish version: https://t.co/gFAjPQ5clS

#AI #MachineLearning #Statistics #RStats

2/🧵 Allow your approach to be sloppy at first and burn some of your initial time, energy, and data on informing a good direction later. That's right, you're supposed to start sloppily ON PURPOSE.

3/🧵 Have a phase where the only result you’re after is *an idea of how to design your ultimate approach better.*

4/🧵 In other words, start with a pilot phase where the objective isn't finding answers, it's finding a good approach to finding answers.

5/🧵 That means you're encouraged (ENCOURAGED!) to start with everything your stats classes told you not to do:
MACHINE LEARNING
Pratham Prasoon
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)
MACHINE LEARNING

You May Also Like

Jaynesh Kasliwal
Jaynesh Kasliwal
@JayneshKasliwal
A simple #swingtrading strategy
1. Whenever you see a stock in strong uptrend it will tend to take support on its 21 ema.
2. Always look whether the stock has taken support previously.
@kuttrapali @rohanshah619 @chartmojo @chartworldat
#adaniports #balajiamine #jswsteel


3. 21 ema will act as dynamic support in a trending market
4. Risk: Reward is favourable in such setups
5. 50 ema can also act as support which can be kept as stoploss for swing trading
6. Volume should be less during pullbacks .
#nifty50 #stockmarket #CHARTS
STOCKLEARNINGS , ALL
Vibhu Vashisth
Vibhu Vashisth
@VIBHU_Tweet
RANI GAIDINLIU:THE LESSER KNOWN FREEDOM FIGHTER

Rani Gaidinliu joined the freedom struggle at 13 &was sentenced to life imprisonment at 16."We r free people—the White should not rule over us.”Thus calling out to her Zeliangrong tribesmen was the voice of 13yr-old Rani Gaidinliu.


She joined the freedom struggle in the present-day Northeast India. Today, her struggle is lost in history as most of her countrymen wouldn’t even have heard her name. B'coz our history textbooks tell us that only Mahatma Gandhi &Pandit Nehru got India its Independence.


At 16 yrs of age, this valiant girl was sentenced to life imprisonment for leading a movement to drive out the colonial rulers from Manipur and Nagaland. Nevertheless, she was released in 1947 after India’s independence and was given the title ,"Rani of Nagas".


EARLY LIFE AND HERAKA MOVEMENT

Gaidinliu belonged to the Rongmei clan of the Zeliangrong tribe in the Tamenglong district of western Manipur. Born on January 26, 1915, she was fifth among eight children.


Her native village was Nungkao, which is present day Tamenglong distt. Brought up in a specially backward region,she couldn't receive any formal education. However,this didn't stop her from joining the freedom struggle. At the age of 10 she came under the influence of her cousin.
ALL
Advertisement
Nikita Poojary
Nikita Poojary
@niki_poojary
Mr. Vijay Kedia built a net worth of over Rs. 800 crores.

But you probably never read past that headline.

So I binged hours of interviews to learn his investing principles and strategies.

Here are 20 lessons on investing from @VijayKedia1 Sir:

Collaborated with @AdityaTodmal


Before I start, a quick disclaimer, please don't ape his portfolio.

As the entry price, horizon and risk appetite would be far different than yours.

Rather lets draw inspiration and try to learn his stock picking skills.

Now let's DIVE IN👇

1/ Started off as a trader:

- Soon, beginner’s luck started to fade out and loses started to mount, to an extent where his mother was about to sell her ornaments.

- Although he was able to dodge the situation.

- This incident taught him the biggest lesson to have a stop-loss.

2/ Punjab Tractors:

- In 1990, he made his first investment by putting in his 10-years savings of Rs 35,000 in this stock, based on a news trigger that tractor industry will witness a turnaround.

- It worked and fetched him 4-5 times which he calls it as a fluke.


3/ He believes that an investor must possess three qualities:

i. Knowledge,
ii. Courage, and
iii. Patience.
GENERICLEARNINGS , ALL
Jaya_Upadhyaya
Jaya_Upadhyaya
@Jayalko1
ANTARVEDI LAKSHMI NARASIMHA SWAMY, EAST GODAVARI DIST.(AP)

Located where Vasistha Godavari joins Bay of Bengal.

Present structure was built by Kapanati Krishnamma of Agnikula Kshatriya clan in 1823.

It is one of the oldest among 32 Narasimha Kshetras in AP.
@LostTemple7


Legend says that here Maharishi Vasishta prayed to Narasimha to end the demon Rakta Vilochana.

Narasimha created Maha Maya, also called Ashwaroodambika or Gurralakka to suck his blood as he got a boon from Brahma that blood falling from his body would produce another demon.


After his death, the stream of blood was let out by Maya to form a pond called Rakta Kulya.

Narasimha,then,washed Sudarshan Chakra at a place called Chakra Tirtha.

Brahma is said to have performed Yagna and installed Shiva Linga here. Hence the place was called Antarvedi.


Later Sri Rama prayed here and Arjun also visited here.

Panchamrita Abhishekam is done every day.
One can have Nijarupa Darshanam (main murti without any decorative shield) between 6.00 a.m. and 8.00 a.m.

Anna Prasadam is very famous and distributed daily from 10:30 to 2 pm.
ALL
Noah Smith
Noah Smith
@Noahpinion
1/Politics thread time.

To me, the most important aspect of the 2018 midterms wasn't even about partisan control, but about democracy and voting rights. That's the real battle.

2/The good news: It's now an issue that everyone's talking about, and that everyone cares about.

3/More good news: Florida's proposition to give felons voting rights won. But it didn't just win - it won with substantial support from Republican voters.

That suggests there is still SOME grassroots support for democracy that transcends

4/Yet more good news: Michigan made it easier to vote. Again, by plebiscite, showing broad support for voting rights as an

5/OK, now the bad news.

We seem to have accepted electoral dysfunction in Florida as a permanent thing. The 2000 election has never really
POLITICS