Deep, Trippy, Robotic Dreams

So over the past few weeks or so the internet went crazy over Google’s brilliant artificial intelligence research, called “DeepDream”.

DeepDream is a research on artificial neural networks by Google primarily focused on computer vision and image classification.

Artificial neural networks are a very prominent and upcoming field in machine learning. These learning models are based on the biological neural network, consisting of various layers of “neurons” which process and input by forming links between multiple neurons and piecing bits of information together. The stronger these links are, the more detailed the output is.

 

DeepDream specifically focuses on interpreting visual information, identifying patterns and objects in the images that are fed through the network of neurons. These neurons have been fed millions of bytes of visual information in order for it to understand the fundamentals of certain objects, allowing it to detect patterns and identify objects in images.

Source: Google Research Blog

Now here comes the cool part.

When these neural networks are fed images, they detect existing objects based on what it can identify as an orange or a banana. So essentially these machine brains have a preconceived idea of what a certain object would look like. As such, when they are fed empty noise and told to search for bananas, they output this:

Source: Google Research Blog

Wait what???! Did a machine just create these bananas by itself???!

Yes and no. The neural network basically digged up every image of a banana in its database and tried to find similarities between bananas and the noise that it was fed. And when it tried hard enough, it found a couple of bananas in an image that we perceive as pointless noise.

Fascinating, ain’t it? Here’s a couple more:

Source: Google Research Blog

Google calls this “Inceptionism”, similar to the idea of the Nolan film, where a thought planted in your mind grows to become a reality. Similarly these artificial mirrors of the biological brain have some bias towards the images that they percieve, based on the keyword that is fed into the system, the “planted thought”.

And it doesn’t end there. When these dream images are fed back again and again into the neural network to be processed recursively, magic happens.

Source: Google Research Blog

SAY WHUTTTT????!?!?!??

These magnificent and wondrous dreamy landscapes come out of nothing more than a bunch of circuits and wires. Machines fed meaningless noise are able to churn out complex architectural and natural marvels, simply through neural connections. Wow. Simply mind blowing…

And it makes you wonder, what reality is really made of? If a bunch of 20-30 artificial neurons are able to produce dreamy landscapes and virtual realities, then what about the 100 billion neurons in the average human brain? If a keyword can visualise noise for a machine, then don’t the numerous external stimuli play a significant role in what we percieve the world to be?

It is rather exciting to see the direction in which the research in the field of artificial intelligence is headed. Through studying neural networks and how they work, maybe we could move one step closer to breaking the code behind how the human mind works and how we perceive the vast universe around us.

Maybe if I can I’ll try play around with the source code for DeepDream, and will post the results here if I get something cool. To end off this fascinating post, here’s a trippy video of how the DeepDream processes images and sees patterns.

Till next time! Keep glitching!

Faith in Music in Faith

You know the time when you’re going home after a long day at work, and your all time favourite jam comes up on the radio, and you feel like the king of the world? Or the other time you were feeling depressed, and this one song your friend had shared on Facebook seemed to talk about your entire life story? Or that time you went clubbing and the DJ drops the bass so good that every particle in your body feels exploded with energy and passion and the entire universe feels infinite? Okay maybe that was a little exaggerated, but you get my point.

Music has timelessly had the ability to connect and shape people. Regardless of societal background, whether you are waitressing at the local bar, or making millions at an investment firm, music touches, connects and flows through you.

But humans being programmed to be humans, we always need approval for the shit we do. So we go around judging and dissing others if they aren’t the same as us.

“Dude you listen to Justin bieber?? Are you gay or something?”

“What do you mean you’ve never heard of Metallica??”

“Look at these hipsters and their indie shit”

Okay yea, I admit I’m guilty of this myself.

Naturally we tend to connect with people whom agree to our tastes and preferences. And that’s perfectly fine. If death metal makes you feel infinite and immortal, then that’s awesome. Maybe pure instrumental alone is what you keeps you going through your day, that’s awesome too. Everyone has got their own tastes and preferences in everything they do.

But society doesn’t wanna let you listen to your music. Society wants to tell you that Taylor Swift is music and anything else is crap (no hate on Tay Tay). Society tells you that if you listen to EDM you gotta be some sort of a party animal or druggie/alcoholic. And all these hardcore fans take it to the internet to debate on what good music really is. And these debates can sometimes turn a little ugly, making very personal offensive insults towards the artists or musicians themselves. And the little judgement and insults become hatred and rage. Where does all this hatred come from?

Fear is the path to the dark side.

Fear leads to anger. Anger leads to hate. Hate leads to suffering.

As Master Yoda said once, fear is the path to the dark side. Fear is the root of all negativity. Fear of societal acceptance. Fear of being different. Fear of losing your identity. And that fear acts as a motivation to hate on others, to judge and to diss and attack and shoot them down through all means.

Hello world!

In line with every prominent first step, “Hello World!”.

The history of “Hello World” is rather interesting. For something so widespread among the programming community, the term was first coined based on a reference made in a comic, by  Brian Kernighan,  renowned computer scientist whom played a major role in the development of the UNIX operating system.

Moving on from fun facts, I want to briefly introduce this blog as well as myself in this post. I hope that this post will serve as a sneak peak into the kind of things to expect from this blog, as well as remind the future me why I wanted this in the first place.

There were three main reasons that motivated me to start this blog. Firstly, it serves as means of documenting some of the many thoughts and realisations that having been recurring in the recent months. Secondly, I hope it acts as a personal progress gauge, in tracking how my thought process evolves through experiences and varying phases in life. And lastly, cause every other medium has become means of inflating egos rather than minds.

Therefore, “Glorified Glitches” was born.

What does that even mean? To be honest I didn’t really give it much thought, the name sort of stuck on to me and it sounded hipster enough. Maybe through the progress of the blog the name may change, or the posts may define the term. Hopefully the latter happens, that would be cool.

And with that, the rather generic post comes to an end. Haven’t given much thought about the next post yet, but I do hope to keep this ball rolling and not let friction and air resistance take control.

Till then, keep glitching!