Generative Adversarial Networks (GAN) shook up the deep learning world. When they first appeared in 2014, they proposed a new and fresh approach to modeling and gave a possibility for new neural network architectures to emerge. Since standard GAN architecture is composed of two neural networks, we can play around and use different approaches for those networks and thus create new and shiny architectures, like Adversarial Autoencoder.
The path to learning story of Restricted Boltzmann Machine is bumpy. First, we needed to learn what are Energy-Based Models, the group of machine learning models that Restricted Boltzmann Machine is a part of. Then we need to explore functionalities…
This major idea, first presented by Ian Goodfellow from the University of Montreal back in 2014, is still regarded as one of the biggest breakthroughs in the field. Facebook’s AI research director Yann LeCun called this concept “the most interesting idea in the last 10 years in Machine Learning”.
Deep Learning zoo is getting bigger by the day. This is probably due to the fact that we are "crossing the chasm" with this technology and that we are entering "early majority" phase. Simply put, people find more and more ways…
First of all, let me start this article by stating that GrowIT conference in Novi Sad was awesome. It is the exact thing that was missing in our local IT Community, and it seems that the organizers of the conference ticked…
In one of the previous articles, we started our journey into the world of Autoencoders. We saw that they are one special kind of neural networks, that was able to utilize techniques of supervised learning for unsupervised learning. One might…
Ten years ago not many of us had been fortunate to own a smartphone. Nowadays that number has drastically improved, and it is increasing every single day. The number of daily registered Android and iOS devices is crazy. Take a…
All neural networks architectures lay on the same principles. There are neurons with biases and activation functions connected with weighted connections. However, different problems require the different mix of those neurons and connections. That is how we ended up with…
Not many people know, but apart from doing all techy stuff, I sometimes make music. I even have few EP releases and one album. They are terrible, but hey, it is something to pass the time. Anyhow, after getting deeper…
When people search for information over search engines such as Google or Yahoo, there are pages generated for every query (abbreviated as SERPs), from which Internet surfers get to choose the option that gives them the best information on what…
