Name: João Carlos Néto
Type: User
Company: USP/POLI-LARC
Bio: PhD at Polytechnic, USP, Brazil, and Visiting Scholar at UCLA. Researching in homomorphic encryption, artificial intelligence, and quantum algorithm.
Location: Sao Paulo/Brazil
Blog: http://www.larc.usp.br/en/profile/joao-carlos-neto
João Carlos Néto's Projects
Refactored, clarified versions of programs from http://deeplearning.net/tutorial/ with tests.
Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101
Conversation models in TensorFlow. (website removed)
A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
Noise supression using deep filtering
DeepSpeech neon implementation
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Example models using DeepSpeed
German Morphological Analyzer
DeText: A Deep Neural Text Understanding Framework for Ranking and Classification Tasks
A repository linking to publicly available dialog datasets. Feel free to send pull requests.
Large-scale pretraining for dialogue
Hunspell UTF8 dictionaries. These work with Sublime Text. [Spell check]
Try out deep learning models online on Google Colab
DQW is an EDA tool for training data.
The source code for DrakonHub.com
Language, engine, and tooling for expressing, testing, and evaluating composable language rules on input strings.
Open source copy of my book Natural Language Cognitive Architecture
Example code for "Real-World Natural Language Processing"
Learn how to process, classify, cluster, summarize, understand syntax, semantics and sentiment of text data with the power of Python! This repository contains code and datasets used in my book, "Text Analytics with Python" published by Apress/Springer.
Enhanced Subject Word Object Extraction
Analyze your code locally using a GPT LLM.
An Explainable Leaderboard for NLP
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Faker is a Python package that generates fake data for you.
Super easy library for BERT based NLP models
The fastai book, published as Jupyter Notebooks
Findpapers: A tool for helping researchers who are looking for related works