Navid Dadkhah

Navid Dadkhah

B.S. Student in CS @ Shahid Beheshti University

Projects

AI Projects - Software Projects - Hardware Projects

AI Projects

  • Developed a News classification model using Artificial Neural Networks (ANN) to categorize news articles into predefined categories.
  • Preprocessed the dataset with tokenization and vectorization techniques, and trained the model on different categories of news.
  • Implemented the Lunar Lander problem using Deep Q-Networks (DQN) and Dueling Double DQN (D3QN) architectures to justify the desired location.
  • It is trained in different epochs and generates rewards for each epoch.
  • Implemented the Swimmer-v4 environment using Reinforcement Learning techniques to teach a simulated agent how to swim through a continuous control task.
  • Trained the agent to optimize its movement in water-like environments by maximizing reward, and improving efficiency with each episode using PPO algorithms.
  • Implemented the CartPole-v1 environment using Reinforcement Learning algorithms to balance a pole on a moving cart.
  • Trained the agent through different learning approaches, optimizing performance and stability while maximizing rewards in this classic control task.

Tron Game with AI (Jun . 2023) LINK

  • Implemented a Tron game AI using Minimax and Genetic algorithms for decision-making.
  • Agents try to build walls while avoiding collisions, using wall-breaking mechanics strategically.
  • Minimax predicts moves by simulating future game states, while the Genetic Algorithm optimizes decision-making.
  • Developed a series of image processing and computer vision techniques to analyze and process images for feature extraction and classification.
  • Applied various algorithms to enhance, segment, and classify images, focusing on improving the accuracy and efficiency of visual recognition tasks.

Software Projects

  • Implemented the Cocke-Younger-Kasami (CYK) algorithm to parse and validate strings against context-free grammars.
  • Applied the algorithm to efficiently check whether a given string can be generated by a specific grammar, showcasing its application in syntactic analysis.
  • Developed a web-based restaurant management system using Django for the backend and React for the frontend.
  • Implemented features for browsing restaurants, making reservations, and managing user roles with different access levels for customers, restaurant admins, and system admins.
  • Developed simulations for various types of graphs, including Erdős–Rényi, Watts–Strogatz, and Barabási–Albert models.
  • Analyzed graph properties such as degree distribution, eigenvalue distribution, and algebraic connectivity, implementing methods for generating and simulating real-world graph behaviors.

Hardware Projects

  • Created a version of the classic Doodle Jump game in Assembly 8086, implementing platform generation, player movement, and score tracking.
  • Developed the game mechanics to ensure smooth and responsive gameplay, with features such as random platform placement and increasing difficulty over time.