Inspired by the neural style algorithm in the computer vision field, we propose a high-level language model with the aim of adapting the linguistic style.
Deep neural network architecture for representing robot experiences in an episodic-like memory which facilitates encoding, recalling, and predicting action experience - Research Project at KIT's High Performance Humanoids Technologies Lab (H2T)
Ilustração de como podem ser construídos diversos indicadores técnicos utilizados no mercado financeiro para criação de estratégias de trading usando machine learning e deep learning.
Automatically describing the content of an image fundamental problem in artificial intelligence that connects computer vision and natural language processing. Being able to build a model that could bridge these two fields will help us apply various techniques of each other to solve a fundamental problem in artificial intelligence.
A self-driven project utilizing ARIMA, Seq2Seq, and XGBoost to help design the COVID19 forecasting algorithm. Data sources are from Kaggle Competition and JHU CSSE.