Front Picture

Hi, Nice to meet you!

My name is Padam Thapa, an MS student in Computer Science at the University of New Orleans (UNO), specializing in Machine Learning and Deep Learning for Computer Vision. My research focuses on leveraging advanced AI techniques to identify and localize defects in levee systems using sensor data, UAV-captured imagery, and synthetic datasets generated through GANs, Diffusion Models, and Unity3D. I have developed robust pipelines for real-time segmentation, object detection, and annotation automation, significantly improving efficiency and accuracy in levee fault detection. My work includes building scalable full-stack pipelines for real-time inference, enhancing dataset diversity with diffusion models, and applying model quantization techniques to improve efficiency.

My Skills

Python, R

85%

Tensorflow-Keras, Pytorch

90%

Sklearn, Pandas, NumPy

80%

Matplotlib, Seaborn, plotly

85%

SQLite, MySql, PostgreSQL

70%

MS Excel, VBA Excel

90%

DynamoDB, MongoDB

60%

Elasticsearch

60%

Django, Flask

65%

PowerBI

75%

Microsoft Azure, AWS

45%

Others: Git, Pytest, NLTK, Streamlit, MLOps

80%

PROJECTS

Microsoft Malware Prediction

The ML model where the malware is detected automatically when the user happens to interact with the Trojans or Worms. Out of the 3 algorithms used, XGBoost outperformed the best.

Stock Price Prediction

An AI model trained with Nepal Stock Exchange dataset to optimize  stock trading strategy and outcome with maximum investment return  using Deep Reinforcement Learning and LSTMs.

Credit Card Fraud Detection

Used highly imbalanced transactions dataset with 3 classification models  trained with both imbalanced and synthetically balanced datasets.

Detecting COVID-19 with Chest X-Ray

Used a ResNet-18 model and trained it on a COVID-19 Radiography dataset  to create an Image Classification model that can predict Chest X-Ray scans with reasonably high accuracy

Traffic Sign Classification

A multi-class Classification project using Deep Convolutional Neural  Network Model which can classify the images of 43 distinct types of  Traffic Signals.

Explainable AI: Scene Classification using ResNet-18

A Deep CNN and ResNet Model trained for classification of scenary  from Satellite Images using GradCam visualization technique  which helps to explain how AI models think.

Contact

Contact Info

Leave a response.

Or just say hi!.

Address

United States of America

Send Message