Skip to content

5i5ousPlay/Modified-PARNet-Time-Series-Classification

Repository files navigation

Modified PAR-Net for Time-Series Classification

This project investigates a modified version of PAR-Net, a dual-stream architecture that combines a Convolutional Neural Network with an Echo State Network reservoir and temporal attention.

Unlike the original architecture, the implementation preserves the full reservoir-state trajectory and aligns it with the CNN feature sequence before applying multi-head attention. Selected reservoir parameters are also made trainable, allowing the model to adapt its temporal dynamics to the classification task.

The architecture was evaluated on the FordA and FordB time-series classification datasets and compared against:

  • A baseline CNN
  • A CNN with multi-head attention
  • The modified CNN–ESN–attention architecture

Experiments used the official dataset splits and five-fold cross-validation. Results showed that the reservoir-enhanced model achieved modest, consistent improvements under clean conditions, while the attention-only model was generally more stable under noisy distribution shifts.

Files

  • 211591_CONANAN_CSCI214_FinalPaper.pdf — project paper
  • 211591_CONANAN_CSCI214_FinalPaper_Code.ipynb — model implementation and experiments

Documentation

Technologies

Python, PyTorch, NumPy, scikit-learn, pandas, and matplotlib

Author

Raul Jarod Conanan

Developed as the final project for CSCI 214.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages