There are 2 repositories under model-training-and-evaluation topic.
Unlock the potential of finetuning Large Language Models (LLMs). Learn from industry expert, and discover when to apply finetuning, data preparation techniques, and how to effectively train and evaluate LLMs.
Successfully developed a machine learning model which can accurately predict whether a firm will become bankrupt or not, depending on various features such as net value growth rate, borrowing dependency, cash/total assets, etc.
This repository contains a project showcasing Federated Learning using the EMNIST dataset. Federated Learning is a privacy-preserving machine learning approach that allows a model to be trained across multiple decentralized devices or servers holding local data samples, without exchanging them.
Leveraging data-driven approaches to mitigate Credit Risk and optimize financial strategies in the banking sector.
An Image classifier model and builder for binary image classification.
Multi-class classification model to predict outcomes of cirrhosis patients using machine learning
This Machine Learning repository encompasses theory, hands-on labs, and two projects. Project 1 analyzes customer segmentation for marketing using clustering, while Project 2 applies supervised classification in marketing and sales.
This project, you will build a full AI pipeline for an image classification task using Convolutional Neural Networks (CNNs). The project will cover data ingestion, preprocessing, model training, deployment, and CI/CD integration using GitHub Actions, Docker, and AWS.
This project aims to build a machine learning pipeline that predicts customer churn using AWS services like SageMaker for model training and deployment, along with Docker for containerization.
🏡 Empower property market decisions with a machine learning model predicting house prices using the Boston Housing dataset. 💸🏠💹
This project aims to predict the risk of student attrition by analyzing various features, such as academic performance, attendance, and involvement in extracurricular activities. By utilizing machine learning models, this project provides insights into potential risk factors for student dropout and suggests proactive measures for student retention.
The Employee Attrition Control project uses data analysis and predictive modeling to understand and address employee turnover. It provides insights and recommendations to reduce attrition and improve employee satisfaction and retention.
This is my public repository with mostly experimental code I write while exploring or creating various deep(or not so deep) neural networks.
This repository contains code for predicting house sales prices using machine learning models. It includes data preprocessing, model training, evaluation, and prediction on test data.
I deployed this bi-disease prediction model in python using Machine Laerning. Deployed this ML model as a web application on cloud streamlit. To see the model please visit
AutoML-MLOps is a comprehensive platform that simplifies the machine learning workflow by automating model development, training, and deployment. With features like real-time dashboards, interactive data visualization, and automated target selection, it enables both beginners and experienced data scientists to save time and improve model accuracy.
A real-time, end-to-end machine learning application built with Flask and integrated with MLflow for tracking and model management. The application predicts house prices based on user input, leveraging trained regression models and providing a web interface for seamless interaction.
Fake News Prediction Model
A minimalist, high-performance Flask REST API Template with built-in rate limiting and best practices.
Heart failure is a severe condition in which the heart is unable to pump blood effectively. Early prediction of heart failure can significantly improve patient outcomes. This project aims to build a predictive model using machine learning techniques to identify patients at risk of heart failure.
Project made for Data Science & MLOPS Bootcamp from Edvai - 6th week exercise
NU Bootcamp Module 21
Our project aims to revolutionize driver safety by implementing a state-of-the-art Deep Learning model designed to detect signs of driver drowsiness, unease, or sleepiness in real-time. Leveraging computer vision technology, the system analyzes data from in-car cameras to monitor facial features and eye movements.
A Python implementation of multiple linear regression to predict the profit of startups based on their spending in R&D, Administration, Marketing, and the state they operate in.
This project implements **Random Forest Regression** to predict the salary of an employee based on their position level. Using a dataset that includes position levels and corresponding salaries, this project demonstrates how an ensemble method like Random Forest can improve prediction accuracy by averaging multiple decision trees.
In this project, I've created an end-to-end ETL pipeline and subsequently developed a machine learning model to predict the price of Amazon products based on several product-related features.
Successfully developed a text classification model to predict whether a given news text is fake or not by fine-tuning a pretrained BERT transformed model imported from Hugging Face.
Successfully developed a fine-tuned DistilBERT transformer model which can accurately predict the overall sentiment of a piece of financial news up to an accuracy of nearly 81.5%.
This project forecasts the total wind and solar electricity production using Long Short-Term Memory (LSTM) neural networks implemented in PyTorch. The model leverages time-series data to predict future renewable energy generation, helping to optimize energy management and grid stability.
Explore advanced neural networks for crafting captivating headlines! Compare LSTM 🔄 and Transformer 🔀 models through interactive notebooks 📓 and easy-to-use wrapper classes 🛠️. Ideal for content creators and data enthusiasts aiming to automate and enhance headline generation ✨.
using YOLOv7 for shoe detection and ResNet for shoe classification
California Housing Prediction - Full Machine Learning Project with deployment configurations and utilizing cloud databases for storage
This project implements a movie recommendation service with Apache Spark using collaborative filtering.
ISeeYou is a model designed for binary image classification using the Boat-MNIST dataset. The dataset provides a simple hands-on benchmark to test small neural networks on the task of distinguishing between images containing watercraft and other images.
This project aims to train a predictive model to diagnose diabetes on women patients.