Bisuraj Sharma's starred repositories
multipleWindow3dScene
based on bgstaal/multipleWindow3dScene
Hacktoberfest
Hacktoberfest OPEN FIRST Pull Request 🎉
ask-my-pdf
Question answering system for PDF files
langchain-rag-pattern
samples for langchain RAG pattern
chat-your-data
Chatbot application built using Next.js, React, and OpenAI. This project allows users to communicate with an AI-based chatbot that provides relevant answers to users' queries. The application uses natural language processing (NLP) technology to understand users' queries and provide accurate responses.
Realtime-Document-Chat-System
In this project, we used Langchain to create a ChatGPT for your PDF using Streamlit. We built an application that allows you to ask questions about a PDF document and get answers directly from an LLM (Large Language Model), like OpenAI's ChatGPT.
QandAForum
An online forum for university students to ask questions and get answers
student-resource-forum-website
A project on Question & Answering Forum like Stackoverflow or Quora
Quora-Clone
**THIS THING IS PRETTY BAD AND SHOULDN'T BE USED** This is a website with similar features to Quora made as a term-long project for my web and databases class in early in 2016. It's fairly messy, and has a lot of questionable design decisions, but it was a project made to learn most of this stuff. I don't plan on ever updating this, it's mainly here for archiving purposes. I am in no ways associated with Quora.
Instagram_Fake_Account_Detection
Detect Instagram Fake Account using Machine Learning approach
Iot-Cyber-Security-with-Machine-Learning
IoT networks have become an increasingly valuable target of malicious attacks due to the increased amount of valuable user data they contain. In response, network intrusion detection systems have been developed to detect suspicious network activity. UNSW-NB15 is an IoT-based network traffic data set with different categories for normal activities and malicious attack behaviors. UNSW-NB15 botnet datasets with IoT sensors' data are used to obtain results that show that the proposed features have the potential characteristics of identifying and classifying normal and malicious activity. Role of ML algorithms is for developing a network forensic system based on network flow identifiers and features that can track suspicious activities of botnets is possible. The ML model metrics using the UNSW-NB15 dataset revealed that ML techniques with flow identifiers can effectively and efficiently detect botnets’ attacks and their tracks.
Logistic_Regression-Parallel
A OPENMP implementation of logistic regression.Different version such as stochastic gradient descent and batch gradient version are implemented.Analysis on different parameters to the serial version.
Bottleneck-analysis-of-matrix-multiplications-and-CNN-inference
Bottleneck analysis of parallelized matrix multiplications and CNN inference using OpenMP.
Image-classification-with-C-OpenMP
Image Classification on FMNIST using OpenMP with C
openmpf-projects
Top-level repository containing submodules for other OpenMPF repositories
OpenMP-Code-Generation-In-Polly
This is the place where I store all the data related to my MTech Project
Parallel-Computing-Projetcs
There are 4 projects developed with MPI, OpenMP and CUDA
Lu-Decomposition-in-Parallel
This project uses openMP, MPI, and Cuda to solve lu decomposition
Parallel-word-Search-using-Openmp-and-PHP
This project was developed using Openmp ,C++ and PHP and is an application of parallel computing
Social-Data-Analysis-and-Visualizations-Investigating-San-Francisco-Crime-Scene-using-Police-Reports
This repository contains the collection of Python and Javascript (Observable Notebook) projects made for the DTU Data Science course 02806: Social Data Analysis and Visualizations
Detection-of-HateOffenseAbuse-In-SocialMedia-NLP-Python
The idea is to use various classification algorithms and sentiment analysis to train on twitter and other social media data to develop a model that detects potential cases of cyberbullying or abuse.A classification model was implemented with experiments and analysis carried out for different features and models with about 73% accuracy using random forest with a maximum depth of 60. The analysis and model is explained in the detection-hate-offensive.pdf file which also serves as the technical paper for this research.
HASOC-2021
Automated recognition and detection of Hate Speech and Offensive language on different Online Social Networks, mainly Twitter, presents a challenge to the community of Artificial Intelligence and Machine Learning. Unfortunately, sometimes these ideas communicated via the internet are intended to promote or incite hatred or humiliation of an individual, community, or even organizations. The HASOC shared task is to attempt to automatically detect abusive language on Twitter in English and Indo-Aryan Languages like Hindi. To participate in this task and provide our input, we (team Data Pirates) presented several machine learning models for Hindi Subtasks. The datasets provided allowed the development and testing of supervised machine learning techniques. The top 2 performing models for sub-task A were Naïve Bayes and Logistic Regression with the same Macro F1 score of 0.7394. The top 2 performing models for sub-task B were Logistic Regression and CatBoost, with Macro F1 scores of 0.4828 and 0.4709, respectively. This overview intends to provide detailed understandings and to analyze the outcomes.
nn-zero-to-hero
Neural Networks: Zero to Hero