CNN Image Classification & Regression
Convolutional neural networks for vision classification and regression
Designed and trained convolutional neural networks for image classification and regression tasks. Covered architectural decisions (depth, pooling, batch norm), training pipelines, and evaluation across both categorical and continuous output settings.
PyTorch / Python
Generative Modeling with Diffusion Models
Implementing diffusion-based generative models from scratch
Implemented a denoising diffusion probabilistic model (DDPM) for image generation. Covered the forward noising process, reverse denoising network (UNet), noise scheduling, and sampling procedures.
PyTorch / Python
GNN Molecular Property Prediction
Predicting quantum molecular properties on the QM9 dataset
Trained a Graph Neural Network using PyTorch Geometric on the QM9 dataset to predict quantum-chemical properties of small organic molecules. The model operates directly on molecular graphs, representing atoms as nodes and bonds as edges.
PyTorch Geometric / PyTorch / Python
ML Network Traffic Classifier
Machine learning for network trace classification
Built a machine learning classifier to identify and categorize network traffic types from packet-level trace features. Applied feature engineering on raw packet captures and evaluated multiple classification approaches.
Python / Scikit-Learn / Pandas
Time Series Forecasting
Deep learning approaches to temporal sequence prediction
Implemented and compared deep learning architectures for time series forecasting, including recurrent and attention-based models. Explored sequence modeling, stationarity, and evaluation metrics for temporal prediction.
PyTorch / Python / Pandas
Transformer Sentiment Analysis
Fine-tuned transformer model for text sentiment classification
Fine-tuned a pre-trained transformer model for sentiment classification on text data. Explored tokenization, attention mechanisms, and transfer learning as applied to NLP classification tasks.
PyTorch / Hugging Face Transformers / Python