Yairz1 / AutoEncoder Public

Notifications You must be signed in to change notification settings
Fork 0
Star 4

An implementation of AE LSTM based. We test our architecture on several tasks as reconstructing synthetic time series, s&p 500 stocks, and forecasting s&p 500 stocks based on the decoded information (also known as latent space) features we extract from the AE

4 stars 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 82 Commits
Architectures		Architectures
Utils		Utils
README.md		README.md
lstm_ae_mnist.py		lstm_ae_mnist.py
lstm_ae_snp500.py		lstm_ae_snp500.py
lstm_ae_toy.py		lstm_ae_toy.py
requirements.txt		requirements.txt

Repository files navigation

Results

Synthetic data reconstruction

Mnist samples reconstruction (We treat each image as a vector)

Real S&P 500 stock values reconstruction

About

An implementation of AE LSTM based. We test our architecture on several tasks as reconstructing synthetic time series, s&p 500 stocks, and forecasting s&p 500 stocks based on the decoded information (also known as latent space) features we extract from the AE

timeseries autoencoder machinelearning deeplearning forcasting

Report repository

Releases

No releases published

Packages

No packages published

Contributors 2

Languages

Python 100.0%