Maik Paixão's Projects
Fraud Detection Analysis for Banking Transactions. Advanced algorithms and machine learning models to analyze and identify fraudulent activities in financial transactions.
Bayesian Optimization for hyperparameter tuning in machine learning using a Jupyter Notebook. This repository demonstrates optimizing a Gradient Boosting Classifier with practical examples and clear explanations.
Model Serving Made Easy
Identification of brazilian species of snake using Image Processing and Machine Learning
State-of-the-art Floor Plan Recognition System. This innovative software utilizes advanced algorithms to accurately interpret and analyze architectural floor plans.
DeepIE: Deep Learning for Information Extraction
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
Build a dialog dataset from online books in many languages
The application developed is a chatbot that simulates a presidential candidate. The chatbot is written in Prolog and aims to show the power of the language for use in AI
Housing portolio optimization based on houses properties and survival analysis considering pricing and time on market (liquidity) .
LexNET: Integrated Path-based and Distributional Method for Lexical Semantic Relation Classification
Code and resources for a computer vision project aimed at detecting and extracting information from motor nameplates.
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
Neural relation extraction (NRE) system that utilizes Transformer models, specifically BERT, to identify and classify relationships between entities in text.
Data Science and Machine Learning based techniques to explore the credit card risk of users using the Nubank dataset.
Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP
Pylinguistics an open source tool to readability assessment of texts written in Portuguese and English.
Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs (EMNLP 2020)
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Code for "Active Learning from the Web" (WWW 2023)
Learning embeddings for classification, retrieval and ranking.
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
Improving XGBoost survival analysis with embeddings and debiased estimators