Published:
The whole system consists of different models each suitable for a different situation and it decides automatically based on some parameters which to use the most. Both ALS and DNN have their own pros and cons but in a complementary way. Using them together can be a way of solving popular recommender system challenges. link full document Read more
Published:
The goal of this project is to develop an AI Bot able to learn how to play the popular game Snake from scratch. In order to do it, I implemented a Deep Reinforcement Learning algorithm. This approach consists in giving the system parameters related to its state, and a positive or negative reward based on its actions. No rules about the game are given, and initially the Bot has no information on what it needs to do. The goal for the system is to figure it out and elaborate a strategy to maximize the score - or the reward. We are going to see how a Deep Q-Learning algorithm learns how to play snake, scoring up to 50 points and showing a solid strategy after only 5 minutes of training.(link) Read more
Published:
A voluntary attempt to solve UCBerkeley’s pacman AI project series problems. It starts by implementing simple search algorithms and ends with implementing Q-learning to play as the pacman agent. (link) Read more
Published:
Sharif AI Challenge is a programming competition for all who are interested in artificial intelligence. This competition is held in two phases annually. Including an online and an on-site phase in which competitors will compete in teams of three in a game designed by our technical team. The only pre-requisite to enter this competition is familiarity with programming using C++, Java or python. But obviously, knowledge of algorithmic thinking and artificial intelligence will be a great asset for any of the participating teams. The registration for online competition is free. Read more