| --- |
| language: en |
| license: mit |
| library_name: pytorch |
| tags: |
| - continual-learning |
| - catastrophic-forgetting |
| - information-geometry |
| - spectral-methods |
| - computer-vision |
| metrics: |
| - accuracy |
| --- |
| |
| # Anastrophic Regularization CNN (Split-MNIST) |
|
|
| This model card hosts the weights for a CNN trained using **Anastrophic Regularization ($\mathcal{R}_{ana}$)**, a novel approach to mitigate catastrophic forgetting in sequential learning tasks. |
| |
| ## Model Description |
| Anastrophic Regularization is derived from **Anastrophic Theory**, a mathematical framework for analyzing discrete periodic systems. Unlike standard $L_2$ decay or EWC, this method preserves the structural "Harmonic Memory" of the network by guiding weight evolution along Fisher-Rao geodetic paths. |
| |
| ### Key Advantages |
| * **Maximum Plasticity**: Weights adapt to new tasks while maintaining the global periodic functional invariants of previous ones. |
| * **100% Data-Free**: Operates strictly in the spectral domain via Fast Fourier Transforms (FFT). No access to previous training data is required. |
| * **Privacy Preserving**: Ideal for environments with data-retention constraints where EWC or Replay buffers are not feasible. |
| |
| ## Intended Use |
| This specific model serves as a benchmark for **Continual Learning**. It was trained on the Split-MNIST dataset: |
| 1. **Task A**: Digits 0-4 |
| 2. **Task B**: Digits 5-9 (Trained using $\mathcal{R}_{ana}$ to prevent forgetting Task A). |
| |
| ## Evaluation Results |
| The model achieves the following performance: |
| * **Task B (Current) Accuracy**: ~86.69% |
| * **Task A (Retained) Accuracy**: ~71.16% |
| |
| ## Mathematical Formulation |
| The weights were optimized using the following objective: |
| |
| $$\mathcal{R}_{ana}(W) = \lambda(1 - \Phi(Spec(W))) + \eta BB(W, W_{prev})$$ |
| |
| ## Citation and Full Paper |
| For the complete theoretical framework, proof of the Fisher-Rao geodetic paths, and the original publication, please refer to: |
| |
| **Zenodo Repository:** [https://zenodo.org/records/18699347] |
| |
| **GitHub Implementation:** [https://github.com/MituMath/Anastrophic-Regularization-PyTorch] |
