The final phase of the seminar is dedicated to working hands-on on a project of your choice. They are done in small teams and mentored by one of the lecturers. Here you can see several descriptions of projects done during 4th iteration of Practical Seminar In Machine Learning.
Irena and Nikola: Atari games
Among many interesting topics mentioned in lectures during the course, Reinforcement Learning was the one completely new for us, and as such caught our attention the most. The possibility to create an agent that plays games like a human seemed like a fun start to test our understanding of the concept. Read more…
Ljubomir and Ognjen: Favicon GAN
Among the lectures we heard during PSIML, the Generative Adversarial Network (GAN) lecture caught our attention the most. GANs were invented only a few years ago and are giving impressive results in image generation (e.g. generating human faces so that one cannot tell if they are real or generated by GANs). Read more…
Radenko and Srdjan: Image Captioning
Our project was about Image Captioning. The task was to create a Machine Learning algorithm which will give a one sentence description for a given image as the input. We found Computer Vision to be a very interesting topic. Read more…
Andrija and Jelena: Image Segmentation
During our stay in Petnica, we worked on a project called Image Segmentation. We implemented semantic image segmentation in order to recognize different body parts and clothes on “Look into Person” dataset. We chose this topic because semantic image segmentation is a very present topic in Computer Vision nowadays and can be applied in different situations, which makes it very compelling and relevant. Read more…
Aleksa and Danijel: Rubik’s Cube
When it came to choosing our project, we had a bunch of ideas in the beginning, but after giving it some thought we finally opted for solving Rubik’s Cube problem. Our inspiration was a combination of 2 factors. First one was seeing the high school students from a different seminar in Petnica solve the actual, one or two nights before. Read more…
Luka and Marko: MetalGAN
Somewhat atypically, we started our project by brainstorming on a dataset we wanted to use: a collection of 140k metal album covers with various metadata (artist, release year, genre etc.). Both of us being metal fans, that selection was an easy task, the harder one being to pick which of the many topics we’d learned about at PSIML seemed the most interesting. We settled for trying to generate (new) covers given the subgenre using a type of Generative Adversarial Network (GAN). Read more…
Fredi: Unitary CNN
I worked on the research project “Unitary CNN”. Since I already had some experience with Machine Learning and Deep Learning and did not have any experience with research, I chose to focus on working on a pure research project. The goal was to extend the work of “Tunable Efficient Unitary Neural Networks (EUNN) and Their Application to RNNs” to work with CNN networks and by consequence to work as any linear transformation which is a basic building block of neural networks. Read more…