BC MACHINE LEARNING

Saved by @Alex1Powell

Santiago
@svpino 5 years, 6 months ago 1414 views

Save to PDF Share See On Twitter

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.

👇

5⃣ Focus on the analysis and not the code

In the beginning, spend your time and energy analyzing the problem and its solution.

Code is not important at this stage. Code can come later.

👇

6⃣ Start incorporating new algorithms

As you work through problems, start incorporating new algorithms into your toolset.

Here are a few great options to start:

1. Decision Trees
2. Linear regression
3. Logistic regression
4. Neural Networks
5. KNN

👇

7⃣ Get familiar with a general process to approach problems

Here is a good start:

1. Define the problem
2. Prepare the data
3. Spot-ccheck algorithms
4. Improve the results
5. Present the results

👇

8⃣ Pick a new problem and repeat

It shouldn't be surprising that the best way to improve is to practice and solve new problems.

If you don't have access to real-life problems, get familiar with Kaggle: everything you need will be there.

In the next coming weeks, I'll be posting a whole series of machine learning advice for people wanting to start.

Stay tuned!

More from Santiago

Santiago
@svpino

For a long time, I didn't understand how to use Virtual Environments in Python 🐍.

If this is just, let's end it here and now: 🧵👇

[2] Virtual Environments let you deal with the dependencies that your code has with external Python libraries.

It avoids having conflicts when your projects depend on different versions of the same library.

👇

[3] Let's imagine that you are building your first Python project and you install the "requests" library:

pip install requests

You get version 2.24.0 installed in your system.

👇

[4] A month later, you decide to work on your second project. It also needs the "requests" library.

But the latest version is not 2.24.0 anymore.

Now version 3 is available, and that's the one you want to use!

👇

[5] You could upgrade your entire system to version 3, but then you'll be potentially breaking the first project you built that depends on 2.24.0!

Can you imagine this happening on a server with many more applications running?

👇

Santiago
@svpino

12 machine learning YouTube videos.

On libraries, algorithms, tools, and theory.

↓

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

Advertisement

Santiago
@svpino

11 short programming problems to stretch your imagination and make sure you are staying on your toes.

(Starting with the simple ones, they get more fun as you move towards the end.)

🧵👇

1. Write a function that reverses an array in place.

In other words, the function should not use an auxiliary array to do the work.

2. Write a function that finds the missing number in an unsorted array containing every one of the other 99 numbers ranging from 1 to 100.

3. Write a function that finds the duplicate number in an unsorted array containing every number from 1 to 100.

Only one of the numbers will appear twice.

4. Write a function that removes every duplicate value in an array.

There could be more than one value duplicated. You should remove all of them leaving a single copy of the value.

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.

Santiago
@svpino

Some of the things I've learned in more than 20 years in the tech industry.

You need to hear these.

🧵👇

Listen to more people who don't look like you, don't speak your language, and don't come from the same place you do.

We aren't doing this near enough.

Small habits compound.

No small improvement is too small.

Just aim for something new every day, and you'll be surprised at the end.

Take responsibility.

It doesn't really matter how you feel, I'm sure you could have done better.

Always keep the big picture in mind and never lose the forest for the trees.

Be the person that pulls everyone out of the rabbit holes.

More from Machine learning

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)

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)

Advertisement

Mads Brodt
@madsbrodt

I've applied for a total of 10 development jobs in my life:

- 7 lead to interviews
- Of those 7, 4 was a good fit for me
- Of those 4, 3 offered me the job
- In all 3 cases, I negotiated a better deal

🧵 on what worked for me and what YOU can do to get similar results 👇

1. Apply for the RIGHT jobs. Look for midsize to large companies, not necessarily tech related. These tend to get way fewer applications than traditional tech companies, so it's easier to get your foot in the door - and they also tend to be great environments for learning.

2. Spend time on your application. Make sure your resumé and written application is tailored to the exact position. Recruiters or hiring managers can smell a copy/pasted resumé from miles away. Use as many words from the job spec in your application as possible.

3. Have a portfolio. Show off your skills and some personality on your website. This is a nobrainer for front-end devs, but it's true for other areas too. It's a great way to stand out over other candidates by actually *showing* the value you can create and your experience.

4. Establish personal contact. Send a quick message or make a phone call before applying. Just introduce yourself to the person in charge of hiring and ask a simple question. It's the best way I find to make them remember your application when you submit it.

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.

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?

👇

You May Also Like

$Anu Satheesh \U0001f1ee\U0001f1f3$

Anu Satheesh 🇮🇳...
@AnuSatheesh5

Stories of Guruvayurappan
Shri Krishna Leela

This is a beautiful story of Guruvayurappan. Once there lived in Guruvayur a poor family. Kitta, his wife & kids were struggling for their daily needs. With only a coconut tree in house, he earned a living by selling coconuts.

Kitta was from a low caste family. He was a great devotee of Guruvayurappan. Everyday before going to work he always prayed infront of a picture of Guruvayurappan in his house. His only wish was to worship at Guruvayur & have annadanam in temple. But he was not allowed there

It was Utsavam time in Guruvayur. From far behind kitta and family worshipped Guruvayurappan. Annadanam was given daily and no one was left empty stomach. Only Kitta didn't receive. That night, it was only Kitta's family who was sleeping without food. After temple nada closed

Shri Krishna, dressed himself as a Brahmin went to temple Kitchen. He packed food and went directly to kitta's house. Reaching Kitta's house, Shri Krishna told he was sent by a cook of Guruvayur temple and gave them the food he packed. Kitta and family was very happy seeing food.

When Kitta finished his food, Brahmin asked it will be better if he get a tender coconut( karikku)to drink. Kitta climbed the tree and gave all coconuts to him. After having 1 tender coconut, the Brahmin asked to bring remaining coconuts to Guruvayur temple the next day.

Patrick McKenzie
@patio11

So the cryptocurrency industry has basically two products, one which is relatively benign and doesn't have product market fit, and one which is malignant and does. The industry has a weird superposition of understanding this fact and (strategically?) not understanding it.

If everyone was holding bitcoin on the old x86 in their parents basement, we would be finding a price bottom. The problem is the risk is all pooled at a few brokerages and a network of rotten exchanges with counter party risk that makes AIG circa 2008 look like a good credit.
— Greg Wester (@gwestr) November 25, 2018

The benign product is sovereign programmable money, which is historically a niche interest of folks with a relatively clustered set of beliefs about the state, the literary merit of Snow Crash, and the utility of gold to the modern economy.

This product has narrow appeal and, accordingly, is worth about as much as everything else on a 486 sitting in someone's basement is worth.

The other product is investment scams, which have approximately the best product market fit of anything produced by humans. In no age, in no country, in no city, at no level of sophistication do people consistently say "Actually I would prefer not to get money for nothing."

This product needs the exchanges like they need oxygen, because the value of it is directly tied to having payment rails to move real currency into the ecosystem and some jurisdictional and regulatory legerdemain to stay one step ahead of the banhammer.

Advertisement

Khatvaanga
@khatvaanga

Sri Gurubhyo Namah.
Some tweets on Adi Shankaracharya and in particular the Guru Parampara of @sringerimath. [I had done this series earlier 5 years ago on account of Shishya Sweekaram].

Adi Shankara established the Sringeri Peetham as the 1st of 4 amnaaya peetams.

The four being
1. Sarada Peetam at Sringeri.
2. Govardhana Peetam at Puri
3. Kalika at Dwaraka
4. Jyothir at Badarikashramam.

He installed his 4 most prominent shishyas as heads of the peetams.

Sureshwaracharya was assigned to Sringeri as its head.

Sringeri is a corruption of Rshyashrunga giri.

Rshyashrunga maharshi [and his father Sri Vibandhaka Maharshi] did their tapas at this place.

It is at Sringeri that Shankara spent 12 of His precious 32 years!!

That gives you and idea how much He loved this place.

Rshyashruga maharshi had a horn on his forehead, a result of being born to a deer. His mere presence was enough to shower rains!!

Rshyashrunga was one who led Putrakamesthi Yaagam of Dasaratha Maharaj and which resulted in Sri Rama's birth!!

EverythingOppresses
@SoOppressed

The first area to focus on is diversity. This has become a dogma in the tech world, and despite the fact that tech is one of the most meritocratic industries in the world, there are constant efforts to promote diversity at the expense of fairness, merit and competency. Examples:

USC's Interactive Media & Games Division cancels all-star panel that included top-tier game developers who were invited to share their experiences with students. Why? Because there were no women on the

ElectronConf is a conf which chooses presenters based on blind auditions; the identity, gender, and race of the speaker is not known to the selection team. The results of that merit-based approach was an all-male panel. So they cancelled the conference.

Apple's head of diversity (a black woman) got in trouble for promoting a vision of diversity that is at odds with contemporary progressive dogma. (She left the company shortly after this

Also in the name of diversity, there is unabashed discrimination against men (especially white men) in tech, in both hiring policies and in other arenas. One such example is this, a developer workshop that specifically excluded men: https://t.co/N0SkH4hR35

Matt Fuller
@MEPFuller

They’re shooting into the chamber.