Skip to content

This repository implements Long Short-Term Memory (LSTM) networks and their variants for time series forecasting and sentiment analysis. It uses PyTorch to implement LSTM, GRU, Bidirectional LSTM for time series prediction, and LSTM, 2-Layer LSTM, CNN + 2-Layer LSTM for classifying suicidal vs non-suicidal tweets.

License

Notifications You must be signed in to change notification settings

Hadi-loo/NNDL-CA4-LSTMs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Neural Networks and Deep Learning Course - LSTM

Project Description

This project is a part of the Neural Networks and Deep Learning Course. The project is about the implementation of the Long Short-Term Memory (LSTM) and its variants. The project is divided into two parts.

Forecasting Time Series

The first part is about the implementation of the LSTM and its variants. this part includes the implementation of the LSTM, the Gated Recurrent Unit (GRU), and the Bidirectional LSTM to forecast the time series. The implementation is done using Python and PyTorch.

Suicidal Tweets Classification

The second part is about the application of the LSTM and its variants in the field of Natural Language Processing (NLP). This part includes the implementation of the LSTM, 2-Layer LSTM, and the CNN + 2-Layer LSTM to classify the suicidal and non-suicidal tweets. The implementation is done using Python and PyTorch.

License

This project is licensed under the MIT License - see the LICENSE file for details.

About

This repository implements Long Short-Term Memory (LSTM) networks and their variants for time series forecasting and sentiment analysis. It uses PyTorch to implement LSTM, GRU, Bidirectional LSTM for time series prediction, and LSTM, 2-Layer LSTM, CNN + 2-Layer LSTM for classifying suicidal vs non-suicidal tweets.

Resources

License

Stars

Watchers

Forks