Amrutha Patil's Projects
A Repository for my public profile āØ
Portfolio
Exponentiation with Amazon AWS
Sinusoidal Wave Generation Using Go
Docker-based setup for a Go web server that integrates with Apache Kafka for message queuing and Redis for data storage
LabExample
Deep learning mini project
This repository contains the implementation and results of the 'Backdoor Attacks'. It focuses on understanding and defending against backdoor attacks in machine learning models, a critical aspect of cybersecurity.
Creating simple chatbot using movie scripts from the Cornell Movie Dialogs Corpus based on the PyTorch Chatbot Tutorial.
Implementing convolution operations on an image using CUDA, exploiting different methodologies - basic, tiled, and cuDNN
Optimizing CUDA programs for vector addition and matrix multiplication
Utilization of CUDA Unified Memory to perform vector addition operations on CPU and GPU
Explore PyTorch Dataloader, profiling machine learning training workloads and optimizing system performance
This repository contains the projects done as a part of New York University's course Deep Learning
This project aims to identify trending news stories and tackle the challenge of fake news by applying sophisticated machine-learning techniques to the news articles dataset.
Final Project of NYU's High Performance Machine Learning Course
This project implements a prototype of an embedded system that can determine if a person has stopped breathing for more than 10 seconds, triggering an alert. It is designed to address the need for real-time monitoring of infants to prevent Sudden Infant Death Syndrome (SIDS).
Investigates the performance of computing the dot product in C and Python, using various implementations and optimizations.
This project simulates an RV32I processor in Python, focusing on understanding the fundamental operations and stages of instruction processing.
This repository contains detailed analysis and a project related to various aspects of systems engineering.
Repository for OOP with Java course - KLE Technological University
This project proposes a two-fold strategy combining Fine-Pruning and STRong Intentional Perturbation (STRIP) to address the susceptibility of DNNs to trojan attacks.