Advanced facial recognition system using deep learning and machine learning. Features real-time face detection with MTCNN, FaceNet embeddings, and SVM classification. Demonstrates high accuracy in live video streams, showcasing expertise in computer vision, TensorFlow, and Python programming. Includes comprehensive tutorials and implementation.

Simplify camera trap image analysis with ML species recognition models based around the MegaDetector model

ML prediction model deployed for forecasting the outcomes of League of Legends matches after 10 minutes of gameplay.

Cardiovascular Disease Prediction using NHANES dataset, leveraged (dk what not) classifiers such as SVM, LR, RF, XGBoost, KNN, C5, BaggedCART, etc. Shiny UI for showcasing predictions

Soil Classifier model made using Pytorch

Train a simple text classifier and predict labels - supports ONNX output for performance, language-neutral

This Flask application provides an endpoint to classify e-commerce reviews into predefined categories using LLama3 and Gemini API.

Credit card fault detection using Naive Bayes classifier and Xgboost classifier

Letters and numbers classifier for chess games using computer vision and neural networks.

This project aims to predict bank customer churn using a dataset derived from the Bank Customer Churn Prediction dataset available on Kaggle. The dataset for this competition has been generated from a deep learning model trained on the original dataset, with feature distributions being similar but not identical to the original data.

This project uses the Multinomial Naive Bayes classifier to enhance movie genre classification based on metadata such as descriptions and ratings. Utilizing a dataset from Kaggle, it aims to improve content recommendation systems through accurate genre prediction.

Spam classification is the process of detecting a particular text to be spam or ham

This project was created as part of a job application challenge to showcase my skills. It utilizes a dataset that cannot be shared due to (potential) confidentiality reasons, and no PRs are allowed. F1: 648/900.

Ground water age predictor

Data preprocessing and training on Drug Review Dataset using Hugging Face library

AWS + Typescript: Lambda Function to read a CSV file to be triggered after a file is included in a S3 bucket

This project aims to build a GUI for custom drawing classifier, which user can input their own classes and provide examples of classes to predict further custom drawings.

Atividade prática de Redes Neurais

Japanese derogatory text classifier