thoughtt ...thinking aloud

Level Design with AI + Human Preference!

One of the most exciting challenges in the field of Video Game and Game AI is generating (good) games and levels with no to minimal human intervention. There are few attempts, like Procedural Content Generation, down this line but I believe we still have a long way to go. One of the interesting papers that I have come across is “Co-Creative Lev... Read more

The Science of Averaging!

A couple of months back, I created an average face of all members of Iran’s Islamic Consultative Assembly. It was a quick 5-minute project and It has been done thousands of times. There was nothing special about this project, but something very interested happened when I started to show the results to people outside the field of Computer Science... Read more

Handling Disconnexion!

There are times that your internet connection is heavily monitored, restricted, and firewalled. This could happen when you are behind a corporate firewall, some regions with limited internet connectivity, or mandatory censorship. In these scenarios, there is at least one layer between the actual internet and you. These extra layers perform m... Read more

Randomness of Uninitialized Variables

The other day I came across this interesting question on StackOverflow. The OP is merely asking whether it is a good idea to use an Uninitialized Variable (UV) as a random number generator. There are several answers to this question, from the Software Engineering point of view, it might be a terrible idea; because this kind of code introduces ... Read more

I made a game to better understand CNNs

One of my hobbies is to play with pre-trained models to see how good they perform. Almost always it was clear to me that pre-trained models, like DeepLab or MaskRCNN, are not particularly good at detecting some abstract representations of an object. They are to some extends good at detecting (full) silhouettes, but they perform poorly when they ... Read more