Projects
Machine Learning for 6G CSI-RS Processing
Developed novel machine learning-based methods for CSI-RS (Channel State Information Reference Signal) processing for 6G standards, achieving NMSE in the order of 1e-3 using UNet-inspired architectures.
rawML - ML Implements from scratch
Developed a custom ML library implementing neural networks from scratch in Python and NumPy.
Reinforcement Learning for Hangman Game
Designed a Deep Q-Network (DQN)-based agent to play Hangman by predicting optimal letter choices, using RNNs for memory.
LSTMSE-Net: Audio-Visual Speech Enhancement
Developed LSTMSE-Net, an audio-visual speech enhancement model to isolate and enhance speaker audio in noisy environments using temporal feature extraction with RNN and LSTM units.
Deep Learning for Liver Tumor Segmentation
Developed novel U-Net based deep learning models for liver tumor segmentation, achieving state-of-the-art accuracy of 98% using advanced architectures like Squeeze-and-Excitation Networks and Atrous Spatial Pyramid Pooling.