BC MACHINE LEARNING

Saved by @Mollyycolllinss

Santiago
@svpino 5 years, 4 months ago 1032 views

Save to PDF Share See On Twitter

10 machine learning YouTube videos.

On libraries, algorithms, and tools.

(If you want to start with machine learning, having a comprehensive set of hands-on tutorials you can always refer to is fundamental.)

🧵👇

1⃣ Notebooks are a fantastic way to code, experiment, and communicate your results.

Take a look at @CoreyMSchafer's fantastic 30-minute tutorial on Jupyter Notebooks.

https://t.co/HqE9yt8TkB

2⃣ The Pandas library is the gold-standard to manipulate structured data.

Check out @joejamesusa's "Pandas Tutorial. Intro to DataFrames."

https://t.co/aOLh0dcGF5

3⃣ Data visualization is key for anyone practicing machine learning.

Check out @blondiebytes's "Learn Matplotlib in 6 minutes" tutorial.

https://t.co/QxjsODI1HB

4⃣ Another trendy data visualization library is Seaborn.

@NewThinkTank put together "Seaborn Tutorial 2020," which I highly recommend.

https://t.co/eAU5NBucbm

5⃣ Numpy is another Python library that you will use every single day.

@keithgalli's "Complete Python NumPy Tutorial" is a great start.

https://t.co/Xg0YbuR8fz

6⃣ One of the most basic algorithms that you can learn is Decision Trees.

Watch @random_forests' video where he builds a decision tree from scratch:

https://t.co/tKtUpO1K3l

7⃣ It's hard to talk about machine learning without touching on neural networks.

Probably the best video out there that explains how neural networks work is @3blue1brown's:

https://t.co/OMJHiG7PIu

8⃣ Scikit-Learn is one of the most popular machine learning libraries out there.

@simplilearn's "Scikit-Learn Tutorial" is a great place to start.

https://t.co/efd1kmz07c

9⃣ TensorFlow is the most popular deep learning library that's currently used in the industry.

Here is a massive 7-hour tutorial of TensorFlow 2.0 produced by @freeCodeCamp.

https://t.co/BYUoAQJEeu

🔟 Finally, a great way to start getting familiar with machine learning is the bite-sized recipes published by Google.

This series is worth every minute.

Playlist: https://t.co/xDqhmNQoWg

If you are looking for real-life, hands-on information related to machine learning, follow me.

✌️

If you have questions or suggestions about topics you'd like to hear about, let me know.

More from Santiago

Santiago
@svpino

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)

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.

Advertisement

Santiago
@svpino

Machine learning education is broken.

If you are preparing for a research position, you are good. If you are looking to get out there and start solving problems, not even close.

Here are some thoughts so you can get ahead.

↓

Most classes, courses, and books cover the same road.

They start with a dataset. They finish with a working model. The focus is always on everything that happens in between.

Dataset → Model.

This is great, but not enough.

Real-life situations rarely start with a dataset, and they never end after you finish building your model.

Applying machine learning successfully is hard.

Here are a few examples that you should keep in mind.

First challenge: Properly framing up the problem.

If you don't understand the problem, you can't determine what data you need. If you don't understand the data, you can't build a good model.

I've never seen a company that had their data ready to go.

In fact, most of them don't even have data at all and need you to determine what exactly they should start collecting.

You usually have to go Problem → Potential Solution → Data.

Santiago
@svpino

The two main machine learning techniques used in the industry today:

1. Gradient Boosted Trees
2. Deep Learning

Focus your time learning Scikit-Learn, XGBoost, and a Deep Learning library like Keras or PyTorch and you'll get the most for your time.

If you need to deal with structured data: Scikit-Learn + XGBoost.

If you need to deal with unstructured data (perceptual tasks): Keras or PyTorch.

Of course, there are many more techniques that will be helpful, but if you focus on these you'll be maximizing your ability to deliver value in the short term.

Santiago
@svpino

Do you know what's better than a machine learning model?

Two models.

More than one model working together to solve a problem is called "an emsemble." A simple way to build this is having each model vote for an answer.

But there's a problem with this approach: ↓

I'm gonna focus here on image classification.

Let's assume you built two different models:

• Model 1: A ResNet model.
• Model 2: A one-shot model (Siamese network.)

They both solve the same problem, so you want to combine their results to pick the right answer.

The problem is that you have two models, so voting is not trivial.

What happens in this case?

• Model 1's answer: Class A
• Model 2's answer: Class B

Which one do you select?

Notice that this problem is not limited to an even number of models.

You could have 3 models, each giving you a different answer.

How do you decide which answer to choose?

There are multiple ways to approach this problem. I'll mention a few different ideas on this thread.

Important: Some of these ideas might not be feasible depending on your context. They have worked for me before on different situations, but every problem is different.

More from Machine learning

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.

Pratham Prasoon
@PrasoonPratham

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)

Advertisement

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#,

Pratham Prasoon
@PrasoonPratham

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

Here's everything you need to get started.
🧵👇

In this thread, we'll look at all the concepts in Python you need to know for machine learning along with free resources to help you out.

All of this is based on my experience of successfully teaching 300+ students how to code using Python.

(2 / 19

You can use many languages for machine learning, why Python?

Because of 2 reasons:
- Comparatively easier to learn than other languages
- Has the biggest and most mature community

This makes Python a no-brainer to learn for machine learning as a beginner.

(3 / 19)

These are the absolute basics which you must know about:

- Basic terminal commands
- Basic arithmetic (+,-,/,*)
- Accepting user input
- For & While loops
- Exception handling
- If-Else statements
- Functions, modules & Imports

(4 / 19)

Then comes the more tougher concepts which you must know about:

- Object oriented programming in Python:Classes, Objects, Methods
- PIP (Pypi)
- List slicing
- String formatting
- Dictionaries & Tuples
- Managing environments
- Dunder methods like __init__

(5 / 19)

$Pratham Prasoon \U0001f680$

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)

You May Also Like

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)

Cookie Cyboid
@CookieCyboid

“Why are Tumblr and Facebook cracking down on sex so much? And why is Facebook in so over zealous about it? It’s all Apples fault!” Etc etc

I can explain all. It is largely the fault of a set of US laws called SESTA and FOSTA.

Advertisement

$Dani\xeblle Stotijn$

Daniëlle Stotijn
@DDay35962863

NESARA / GESARA explained for all who are not aware.

"The End of Poverty, The End of Debt, The Beginning of a New Golden Age!"

No Poverty, No Hunger, No Debt, Only Global Prosperity and Peace for ALL

NESARA will merge with GESARA

N = National (US)
G = Global

Aneesh Philomina Anton...
@ProdigalTrader

If u are looking to enter a scrip just before the breakout
what would u look for?
How would u identify scrips just before breakout?

Here are a few pointers
Carefully understand the them and use at ur own discretion
(All comments r compiled from a question i posed)

1/23

Price is testing the same resistance repeatedly since long.
But now in recent times it's forming multiple candles near the same resistance with low volume.
Observe it and see for opposite move.
As soon as u get a positive candle, get in to it.

2/23

1. Volume buildup (vol > when resistance point created) along with, increase in OI, increase in delivery % on HTF
2. On LTF, price stalling around breakout area for at least 1-2hr.
3. No major events.

3/23

Stock reaching breakout LVL with HL-HH
Contraction of price and volume near it especially near 20 days ma.
If there is any breach of the latest HL it should be followed by a bullish candle with good volume.
Left side of the chart has a rally with a very steep slope of ma.

4/23

Number of wide range green bars with high volumes.
If stock is at its ATH then it adds more conviction bcz there wont b supply after that point

Consolidation below the resistance, volume of the candles & strong bullish candle closing at near highs just below the resistance

5/23

$\u0938\u093e \u0935\u093f\u0926\u094d\u092f\u093e \u092f\u093e \u0935\u093f\u092e\u0941\u0915\u094d\u0924\u092f\u0947$

सा विद्या या विमुक्तये...
@raghav_aanya

#ज्योतिष_विज्ञान #मंत्र_विज्ञान

ज्योतिषाचार्य अक्सर ग्रहों के दुष्प्रभाव के समाधान के लिए मंत्र जप, अनुष्ठान इत्यादि बताते हैं।

व्यक्ति के जन्म के समय ग्रहों की स्थिति ही उसकी कुंडली बन जाती है जैसे कि फ़ोटो खींच लिया हो और एडिट करना सम्भव नही है। इसे ही "लग्न" कुंडली कहते हैं।

लग्न के समय ग्रहों की इस स्थिति से ही जीवन भर आपको किस ग्रह की ऊर्जा कैसे प्रभावित करेगी का निर्धारिण होता है। साथ साथ दशाएँ, गोचर इत्यादि चलते हैं पर लग्न कुंडली का रोल सबसे महत्वपूर्ण है।

पृथ्वी से अरबों खरबों दूर ये ग्रह अपनी ऊर्जा से पृथ्वी/व्यक्ति को प्रभावित करते हैं जैसे हमारे सबसे निकट ग्रह चंद्रमा जोकि जल का कारक है पृथ्वी और शरीर के जलतत्व पर पूर्ण प्रभाव रखता है।
पूर्णिमा में उछाल मारता समुद्र का जल इसकी ऊर्जा के प्रभाव को दिखाता है।

अमावस्या में ऊर्जा का स्तर कम होने पर वही समुद्र शांत होकर पीछे चला जाता है। जिसे ज्वार-भाटा कहते हैं। इसी तरह अन्य ग्रहों की ऊर्जा के प्रभाव होते हैं जिन्हें यहां समझाना संभव नहीं।
चंद्रमा की ये ऊर्जा शरीर को (अगर खराब है) water retention, बैचेनी, नींद न आना आदि लक्षण दिखाती है

मंत्र क्या हैं-
मंत्र इन ऊर्जाओं के सटीक प्रयोग करने के पासवर्ड हैं। जिनके जप से संबंधित ग्रह की ऊर्जा को जातक की ऊर्जा से कनेक्ट करके उन ग्रहों के दुष्प्रभाव को कम किया और शुभ प्रभाव को बढ़ाया जाता है।