“Machine Learning” Through “Memes”

Memes are now integral part of our lives as now we are spending hours scrolling them. I personally love memes a lot. Especially, the Science memes. I am an ML (Machine learning) enthusiast too. I love reading about Machine learning and its applications. It really fascinates me that give the data and apply an algorithm and the computer will give and predict something for us. Memes and ML are helping me survive this lock-down. So, I thought to combine them both and see fun what we can have.

If you’re someone who doesn’t know much about ML, here’s what Andrew Ng’s got to say:

He is one of the most renowned personality in the field of ML

Well, What is ML?

Machine Learning Algorithms are those that can tell you something interesting about the data (patterns !), without you having to write any custom code specific to the problem. Instead of writing code explicitly, we feed data to these ML algorithms and they build their own logic based on the data and its patterns.

There’s a lot that is being done using ML. If you see your daily usage, everything from Google Search prediction, Auto correct, weather prediction, Google assistant (or Siri or Alexa), facial recognition; requires and implements ML in one way or another.

Memer’s take on ML

MATH + ALGORITHM = MACHINE LEARNING

And here’s what Wikipedia says about ML:

Machine learning (ML) is the scientific study of algorithms and statistical models that computer systems use to perform a specific task without using explicit instructions, relying on patterns and inference instead.

Here, we had a word Statistics in the definition. Well its a true fact that ML requires a lot of statistics work behind seen and some of the models used regularly are nothing but statistical calculations. So, this:

Also,

Mathematics and ML relationship.

true, indeed 😦

But you don’t need to have had scored an A in mathematics to be able to use ML for your projects or be well versed with these models. And many a people don’t even care about the mathematics behind ML as we already have in-building libraries in python or R which is taking care of that.

Deep Learning

Another term that’s often interchangeably used with ML is Deep Learning

No, not this

So Deep learning is a specific type of machine learning using a technique known as a neural network which connects multiple models together to solve even more complex types of problems.

This is the relation between AI, ML and DL.

Neural networks are a set of algorithms, modeled loosely after the human brain, that are designed to recognize patterns. That’s it. Some nodes or say neurons connected to each other which pass information like the ones in the brain do. Here each neuron processes the info and passes on to the next one. Initially, like a child’s brain, the neural net is random, it hasn’t learnt anything and as we feed data to it, it starts learning. As a child slowly learns features one by one, with increasing complexity, so does a neural network.

Source : Analytics India Webiste

How do you do ML? What is the language? What framework?

Thanks to the modern frameworks (tf, keras, theano, pytorch) used these days, writing code for an ML model has become just a few lines work. You can use Python or even C++ together with these libraries.

So what is Keras?

Keras is a high-level neural networks API, written in Python and capable of running on top of Tensorflow. It was developed with a focus on enabling fast experimentation.

So, What is Tensorflow?

TensorFlow is a free and open-source software library which is a symbolic math library, and is used extensively for machine learning applications such as neural networks. Tf enables you to write complex code in a few lines.

Also, you can use pretrained models and tweak some parameters to get the result of your choice.

So, I hope you have somewhat understood about ML. If you want to know more, feel free to Google it as I’m busy scrolling memes.

Stay cool and learn ML.