muradh2994 Goto Github PK

breast-cancer

ANN is built using Keras library to predict Breast cancer patients

covid_fake_news

covid_fake_news

diabetes-prediction-ml

eda_kc_house_data

face-recognition

facenet_mtcnn

fake-news-detection_bert

flowise

Drag & drop UI to build your customized LLM flow

football-scouting-using-genetic-algorithm

human-and-machine-generated-text-classification-using-graph-neural-networks

In recent times, there has been a significant increase in the amount of text that are generated using machines. For example, chatbots are used to automatically generate chat replies for various customer services. Similarly various machine generated texts are used to promote false propaganda. Further, more recently transformer-based models trained on large corpuses are found to generate text identical to human written text. In such cases, it is important to distinguish between human and machine generated content to identify its authenticity. We propose in this project to investigate the application of graph neural networks to distinguish between human and machine generated text. More specifically, we propose to apply graph convolution networks to use the sentence structure to identify whether a given text is machine generated or human generated.

kerasnn_house-price-prediction

lambda-ai-deployment

Deploying Serverless AI Models on AWS Lambda

langchain_interact_with_csv

langchain_multiple_pdf

langchain_pdf_tutorial

medical_chatbot_genai

ml_employeeattrition

ml_end2end_project

ml_personal-key-indicators-of-heart-disease

mlflowexperiment

pwc-switzerland-power-bi

resnet50_image-classification

rl_10-armed-bandit

rl_cartpole

rl_sarsa-q-learning

titanic-survival

This model is developed using Logistic Regression algorithm to predict the passengers survived in the Titanic Shipwreck