LSTMs for Time Series Forecasting: A Symbolic Approach

Prerequisites

Install Python packages:

pip install -r requirements.txt

Testing

Run the unit tests by the following command:

python unittest_tests.py -v

Example

TODO

• warning if l > length of time series
• make keras training deterministic

License

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

References

[1] S. Elsworth and S. Güttel. Time series forecasting using LSTM networks: a symbolic approach. (In Preparation.)