mohammad's Projects
The goal of this project is to implement and compare two reinforcement learning algorithms, DQN and DDQN, for solving the LunarLander problem.
I implemented a paper on SFOs using GAs. The paper automated SFO design and analysis using different ABBs, and found new oscillator topologies. I used a new fitness scheme, a learning scheme, and a crossover operator. The results rediscovered canonic SFOs using opamps, and new SFOs using OTRA and DDCC.
Communication efficiency is essential for wireless federated learning systems. The objective of this project is to reduce communication costs for federated learning over MIMO MACs.
This is a study of a multivariate optimization problem that aims to find the optimal values of six geometrical parameters of a CBCT system using gradient descent. The cost function is based on the mutual information between the reconstructed and original images.
Distribution and Parameter Estimation using Gibbs Sampling
Config files for my GitHub profile.
Reinforcement Learning Based Maintenance Decision Making for Deteriorating Systems
Software to generate 2D/3D/4D analytical phantoms and their Radon transforms (parallel beam) for image processing