RNA Secondary Structure Prediction using an Ensemble of Two-dimensional Deep Neural Networks and Transfer Learning.

Deep learning anomaly detection on spatio-temporal AIS data by combining a multi-headed self-attention structure with bidirectional long short term memory(BLSTM) into a Variational Autoencoder (VAE).

AB-LSTM: Attention-Based Bidirectional LSTM Model for Scene Text Detection

Regional ADR event detection using Deep Learning

Python notebook to get real time news, save them to mongoDB and get sentiment/relevance (SVM, BLSTM) Docker

Punctuation Prediction Using NER Models.

Trabajo Práctico Final para la materia Organización de Datos 75.06 - UBA. Score máximo obtenido de 0.83726 para la competencia 'Real or Not? NLP with Disaster Tweets' de Kaggle.

Neural network model that predicts the number of syllables in an English word. It shows its creation end-to-end: from data collection to evaluation of various models. One of the explored models is used in the Readgauge app.

This project develops sentiment classification models for IMDB reviews using shallow RNN, unidirectional LSTM, and bidirectional LSTM. It employs GloVe embeddings, evaluates performance with accuracy, precision, recall, and F1 score, and aims to assess the impact of LSTM layers on model effectiveness.