BC MACHINE LEARNING

Saved by @CodyyyGardner

Jan Giacomelli
@jangiacomelli 4 years, 6 months ago 949 views

Save to PDF Share See On Twitter

🤔 Python generators

What are they? How to use them?

#Python

🧵Let's find out 👇

1️⃣ Python generators are lazy iterators delivering the next value when their .next() is called.

They are created by using the yield keyword

next() can be called explicitly or implicitly inside for loop

They can be finite or infinite

2️⃣ yield - where a value is sent back to the caller, but the function doesn’t exit afterward as with the return statement

The state of function is remembered.

For example, the number is incremented and sent back from yield at the consecutive call next()

3️⃣ Generator stores only the current state of the function - it generates next element on next() call and forgets the previous one -> it saves memory

For example, we don't need to store 1mio elements in memory to do something with each element

4️⃣ When you call a generator function generator object is returned - it's not executed yet

It executes only when next() is called

For example, that's why Exception is raised only on the next() call

5️⃣ When the generator goes out of elements it raises StopIteration exception

6️⃣ You can also create a class that behaves like a generator - it needs implemented methods:

- __iter__ -> to enable iteration
- __next__ -> to enable next element access

7️⃣ You can also create a generator with one-liner expression similar to list comprehension

8️⃣ You can read more:

https://t.co/mXp7L8l2Ai

More from Machine learning

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?

👇

Pratham Prasoon
@PrasoonPratham

Can you get a job in data science and machine learning without a college degree?

🧵👇

Short Answer: Yes.

Long Answer, keep reading 👇

(Advice from industry experts who I talked to.)

Companies are looking for people who add value.
In order to add value, you'll need skills. Simple as that.

Get the skills to provide value and you'll get the job.

In the age of the internet where everything is pretty much free, why do college degrees matter?

A college degree makes it easier to get the skills to get a job in machine learning or data science.

College degrees also help you make many useful connections and provides many opportunities in the form of internships and whatnot.

College degrees have their own place

Advertisement

$Prashant \U0001f4da$

Prashant 📚
@capeandcode

Ever heard of Autoencoders?

The first time I saw a Neural Network with more output neurons than in the hidden layers, I couldn't figure how it would work?!

#DeepLearning #MachineLearning
Here's a little something about them: 🧵👇

Autoencoders are unsupervised neural networks whose architecture you can picture as two funnels connect from the narrow ends.

These networks are primary focus for compression tasks of data in Machine Learning.

We feed them the data so that they can learn the most important features, a smaller representation while keep the integrity of the data.

Later when someone needs, can just take that small representation and recreate the original, just like a zip file.📥

Being unsupervised, they require no labels.
Our inputs and outputs are same and a simple euclidean distance can be used as a loss function for measuring the reconstruction.

Of course, we wouldn't expect a perfect reconstruction.

We can think of an autoencoder having two components, encoder and decoder, represented by the below equations:

We are just trying to minimize the L here. All the backpropagation rules still hold.

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.

Marcus Mengs
@mame82

Okay, doing my first baby steps with r2frida (which combines the power of @radareorg and @fridadotre).

Gonna share my progress in this thread (live, so keep calm).

The goal: Runtime inspection of data sent out by TikTok !!before!! it gets encrypted

1/many

First of all, we do not start from zero. I got some prior knowledge from past reversing attempts and want to share some important facts.

TikTok's (log data) encryption is accomplished by a native library. The Android Java code just serves as proxy function to the native function

The decompiled code for the respective native JNI function of an older TikTok version looks something like this, but in this example I use the most current TT version (no statical analysis done, yet)

In case you never reversed native libraries which were build to interface with Android Java layer via JNI, I highly suggest the entry level introduction on the topic by @maddiestone

Before we start, I want to pinpoint some important aspects (which are also covered by Maddie's videos).

1) Unlike raw C-functions, JNI functions like the one showcased above, receive pointers to complex Java objects .

F.e. a function receiving a String on the Java layer...

You May Also Like

Paras Chopra
@paraschopra

1/ Here are my notes from @robertwrighter's book - Nonzero: the logic of human destiny. I enjoyed the book very much.

The basic premise of the book is that history has a direction which favors co-operation and non-zero sum games, and that causes an increase in complexity.

2/ Starting from the first replicating molecule which co-operated with an outer layer to form first proto-cell, evolutionary and cultural history is full of examples where two entities come together to survive and progress a lot more than they would have done individually.

3/ This co-operative entity fares much better than two individual entities because of specialization. If two entities are in the same boat - that they win together or lose together - then trust is implicit.

4/ In a non-zero sum game, trust causes entities to focus on what they do best.

For example, eukaryotic cells - the ones animals and plants have - emerged when two proto-cells merged, and one took the role of energy generator (mitochondria), the other specialized in protection.

5/ Some scientists believe that even nucleus in a cell is a result of an early cell merging with another cell.

So M&A is not a recent phenomena, entities have been merging because of common interests ever since life started.

$Anu Satheesh \U0001f1ee\U0001f1f3$

Anu Satheesh 🇮🇳...
@AnuSatheesh5

Eri Katha Ramar Temple
Maduranthakam

Eri Katha Ramar temple is located at Maduranthakam near Chengalpattu of Tamil Nadu. Beautiful Kodanda Ramar of about 8ft holding Ma Sita's hand & with Lakshmana. This temple story is connected with Sri Ramanujar.
@LostTemple7

It was here Periya Nambigal performed Pancha Samskaaram to Ramanujar under Magizham tree.
Sri Ramanujar was on his way from Kanchipuram to meet Sri Periya Nambigal at Sri Rangam to become his disciple. Sri Periya Nambigal also started towards Kanchipuram to meet Ramanujar.

They both met here at Madurantakam.
Small Mandapam where Ramanujar undertook Pancha Samskaaram is seen in the temple. Separate sannidhi is for Periya Nambigal & Ramanujar & this is the only temple where Ramanujar is seen as a Grahastha (married person) and not in Sanyasa kolam.

Story says about an incident which occurred during British rule. The Madurantakam lake bund was about to breach, due to heavy rain & village will be flooded if it happened. Dt collector was Cl. Lionel Blaze who took efforts to protect the bund & asked for the piles of stones

in the temple to protect it. But it was meant for Janakavalli ( sita) Thayar sannidhi which faced shortage of fund. Lionel Blaze prayed Sri Ramar to save the bund and if so he will provide fund to construct.
That night he saw in the lightning, Sri Rama & Lakshmana walked along

Advertisement

$Brianne Kimmel \U0001f4ac$

Brianne Kimmel 💬...
@briannekimmel

Shocking fact: Millennial men are less likely to work than any other age and gender demographic in America.

Today, there are 500,000 young men missing from the U.S. workforce.

Research suggests video games & improved leisure tech plays a role in the problem. 👇 Thread:

Following the 2007 to 2009 recession, 25 to 34 year old men exited high school with fewer middle-skill job opportunities than years prior.

During this time, we saw an increased number of men living with parents & choosing unemployment over lower paying jobs.

It's estimated that 24M millennials live w/ their parents.

1 in 4 living in their parents’ home neither go to school nor work.

What's more surprising? 9 in 10 who lived with their parents a year ago are still living there w/ no plans to leave.

Economists are calling millennial men a lost generation.

According to economist David Dorn:

“If you get to the point where you’re turning 30, you’ve never held a real job and you don’t have a college education, then it is very hard to recover at that point.”

Economists suggest this choosiness is a generational trait.

Forbes interview w/ a high school educated man:

"I’m very quick to get frustrated when people refuse to pay me what I’m worth."
“People feel that they have choice nowadays, and they

$\u0936\u094d\u0930\u0940\u092e\u093e\u0932\u0940 \u0939\u093f\u0924\u0947\u0936 \u0905\u0935\u0938\u094d\u0925\u0940$

श्रीमाली हितेश अवस्थी...
@HiteshAwasthi89

Sri Parasurameswara Swamy Mandir, Gudimallam, Andhrapradesh

Gudimallam is a small village located in Chittoor district. It is seven miles away from Tirupati. This small village came to significance,due to it's very beautiful Shiva Mandir with history of thousands of years. 1/n

The main importance of the mandir lies in the Linga which is housed in the Garbhagriha of the temple & considered as the only one of such type. It is the earliest Linga discovered so far and it has been assigned to the 3rd century BCE.(Satavahana period) 2/n

$Em\U0001f383jipedia \U0001f4d9$

Em🎃jipedia 📙...
@Emojipedia

✨📱 iOS 12.1 📱✨
🗓 Release date: October 30, 2018
📝 New Emojis: 158
https://t.co/bx8XjhiCiB

New in iOS 12.1: 🥰 Smiling Face With 3 Hearts https://t.co/6eajdvueip

New in iOS 12.1: 🥵 Hot Face https://t.co/jhTv1elltB

New in iOS 12.1: 🥶 Cold Face https://t.co/EIjyl6yZrF

New in iOS 12.1: 🥳 Partying Face https://t.co/p8FDNEQ3LJ