Github Link Tools Used: C++, Graphviz Topics: Deep Learning, Machine Learning Introduction MicroGradCpp is a C++ implementation of MicroGrad, a minimalistic deep learning library. It includes an API to calculate gradients, and to train neural networks in single neuron level. It is a very simple library, and it is very easy to use. It is a very good tool to learn how neural networks work, and how they are trained. ...
Tools Used: Unreal Engine, C++, Blender Topics: Unreal Engine, Game Development, Imperfect Information Games Introduction Dark Hex Online is a multiplayer version of Dark Hex. It is a game where players can play against each other, or against the AI. The game is built on Unreal Engine 5, and is currently in development. The game is still in early stages. We are hoping to release the game on Steam, and we are currently working on the Steam integration. We are also working on adding more features to the game, and improving the game. ...
Github Link Tools Used: Python, C++, Tensorflow, Open-Spiel, Pandas, Numpy, Matplotlib, PyGame, PyDot, Tkinter Topics: Reinforcement Learning, Game Theory, Imperfect Information Games, Deep Learning, Machine Learning Introduction Dark Hex is an imperfect information version of the Hex. Dark Hex is a phantom game, where a player have a chance to play concecutively. Due to this property Dark Hex is an extremely huge game. Which makes it really hard to train agents, and develop algorithms for. ...
Tools Used: Python, PyTorch, OpenAI Gym Topics: Reinforcement Learning, Deep Learning, Neural Networks, Machine Learning Introduction Co-Agent Networks is an actor-critic framework that utilizes some set of interactive nodes. We took this idea under investigation and developed multiple supervised and unsupervised settings that utilizes the nodes as actor-critic agents. The idea of Co-Agent systems is introduced by Philips S. Thomas, and is still being investigated. Features We have developed a fully working framework that utilizes the nodes as actor-critic agents. We have completed multiple experiments and reported the results for the future researchers. ...
Tools Used: Python, PyTorch, Numpy, Pandas, JavaScript, Scikit-learn, Flask Topics: Machine Learning, Deep Learning, Time-Series, Data Visualization, Data Processing Problem The International Space Station (ISS) is a space station, or a habitable artificial satellite, in low Earth orbit. Given that it is in space, with no gravity, air circulation is very hard to manage. Due to lack of circulation any CO2 that is produced by the astronauts is not dispersed, and accumulates in the same area. This can be a problem, as the CO2 levels can reach a dangerous level, and can cause health issues for the astronauts. Especially when they are sleeping, or doing other activities that require them to be in a specific area for a long time. Lack of oxygen first causes dizziness, and headaches, and if the levels are high enough, it can cause unconsciousness, and even death. ...