Evaluate custom and HuggingFace text-to-image/zero-shot-image-classification models like CLIP, SigLIP, DFN5B, and EVA-CLIP. Metrics include Zero-shot accuracy, Linear Probe, Image retrieval, and KNN accuracy.

CS-GY 6953 Deep Learning Major Project

Successfully developed a language detection transformer model that can accurately recognize the language in which any given text is written.

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.

This repository contains codes, datasets, results, and reports of a machine learning project on air quality prediction.

A package to evaluate 3d weather and air quality models

This breast cancer diagnosis project evaluates various machine learning models to effectively classify breast masses as benign or malignant. SVM and Logistic Regression excel in identifying positive cases, leveraging their robust performance metrics, while Neural Networks show promising results and offer opportunities for further enhancement!

Successfully established a machine learning model which can determine whether an individual is vulnerable to the Cirrhosis disease or not by predicting its corresponding stage based on a unique set of medical features such as Cholesterol, Prothrombin, etc. pertaining to that person.

A spam detection model built to handle imbalanced data using small pipelines. This project walks through text preprocessing, model tuning, and performance evaluation with ROC-AUC curves and classification reports, focusing on practical steps like using XGBoost and TFIDF for spam classification.

Quality Prediction of red and white wine

UCI Heart Disease - Feature Engineering and Models Evaluation

Loan Approval Analysis involves building a machine learning model to predict whether a loan will be approved or not based on various customer features

"Linear Regression Step by Step" is a repository that provides a comprehensive notebook with step-by-step examples, exercises and libraries to understand and implement Linear Regression easily.

🗣️ Speech Type Detection is a Flask app to classifies text into categories like "Hate Speech," "Offensive Language," or "No Hate or Offensive Language" with 87.3% accuracy. It offers a user-friendly interface for text input and prediction, using machine learning algorithms. Idea for managing online inappropriate language. 🌐🔍.

Coursera Applied Machine Learning in Python

Analyzed 5,000+ movies with Pandas and Colab to build a machine learning model predicting movie revenue.

This project explores the use of machine learning for fungi classification, developed for the Brisbane Flora and Fauna Society. It combines a DINOv2 Vision Transformer for feature extraction with a custom linear classifier, leveraging transfer learning to classify edible and poisonous fungi species from images.

This project focuses on building a model to predict house prices in California using various features such as location, size, and number of bedrooms. The project includes data cleaning, feature engineering, and model training with Linear Regression and Random Forest algorithms.

Projeto que utiliza a base de dados Iris para calcular a acurácia e a função de perda de um modelo de aprendizado de máquina. Focado em análise de desempenho e avaliação de modelos.

🔍 Evaluating Sampling Techniques for Healthcare Insurance Fraud Detection in Imbalanced Dataset.