In this profile, you will find an overview of my skills, experience, and notable projects. I invite you to explore and learn more about my work. If you have any questions or would like to collaborate, please feel free to reach out.

• Programming Languages: [C , Python, Julia]
• Deep Learning Frameworks: [Pytorch, Sklearn]
• Computer Vision: [Open CV]
• Data Analysis: [Numpy, Pandas, Seaborn]
• LINUX
• Git & github
• Kubernetes and Docker
• Azure & Google Cloud

Here are some of the notable projects I have worked on:

Welcome to the Summary and Sentiment NLP project! This repository aims to provide natural language processing functionalities to summarize text and analyze sentiments. We believe this project has great potential, and we are excited to invite collaborators to join us in making it even better.** It only works for yelp.com aiim to make it better.

The main objective of this project is to develop an NLP application that can summarize lengthy texts and perform sentiment analysis on them. With this tool, users can quickly grasp the essence of long documents and gain insights into the overall sentiment expressed in the text.

This project implements a convolutional neural network (CNN) using the ResNet-34/18 architecture for pneumonia detection from chest X-ray images. It aims to provide an automated solution for accurate diagnosis, contributing to early intervention and treatment of pneumonia.

In this project, I have developed a U-Net model for segmenting blood vessels in retinal images. This segmentation technique plays a vital role in the early detection and monitoring of various retinal diseases, such as diabetic retinopathy.

Using generative adversarial networks (GANs), this project generates realistic human faces. The GAN model learns from a dataset of real faces and produces new, synthetic faces that closely resemble the real ones. This project demonstrates my expertise in deep learning and computer vision.

The U-Net architecture is employed in this project to perform liver segmentation from medical images. Accurate liver segmentation is essential for various medical applications, including surgical planning and disease diagnosis.

Using generative adversarial networks (GANs), this project generates realistic handwritten digits. The GAN model is trained on a dataset of real handwritten digits and is capable of generating new, synthetic digits that closely resemble human-written ones.

This project focuses on image classification using the advanced CNN architecture ResNet-18. The ResNet-18 model is trained on a large dataset and achieves high accuracy in categorizing images into various classes.

In this project, I explore transfer learning and regularization techniques for human protein labeling tasks. The project showcases my understanding of deep learning, transfer learning, and regularization methods in the context of bioinformatics.

Feel free to explore these projects in more detail by visiting the respective repositories. If you have any questions or feedback, please don't hesitate to reach out. I am open to collaborations and new opportunities:

• Email: [[email protected]]
• GitHub: aatmprakash
• Twitter: @aaatmprakash
• LinkedIn: Aatm Prakash

Thank you for visiting my profile, and I look forward to connecting with you!