clarena.cl_algorithms.regularizers
Continual Learning Regularizers
This submodule provides the regularizers which are added to the loss function of corresponding continual learning algorithms. It can promote forgetting preventing which is the major mechanism in regularization-based approaches, or for other purposes.
The regularizers inherit from nn.Module.
Please note that this is an API documantation. Please refer to the main documentation pages for more information about the regularizers:
1r""" 2 3# Continual Learning Regularizers 4 5This submodule provides the **regularizers** which are added to the loss function of corresponding continual learning algorithms. It can promote forgetting preventing which is the major mechanism in regularization-based approaches, or for other purposes. 6 7The regularizers inherit from `nn.Module`. 8 9Please note that this is an API documantation. Please refer to the main documentation pages for more information about the regularizers: 10 11- [**Implement custom regularizers in CL algorithms**](https://pengxiang-wang.com/projects/continual-learning-arena/docs/custom-implementation/cl-algorithm#sec-regularizers) 12- [**A Beginners' Guide to Continual Learning (Regularization-based Approaches)**](https://pengxiang-wang.com/posts/continual-learning-beginners-guide#sec-regularization-based-approaches) 13 14 15 16""" 17 18from .distillation import DistillationReg 19from .hat_mask_sparsity import HATMaskSparsityReg 20from .parameter_change import ParameterChangeReg 21 22__all__ = ["distillation", "hat_mask_sparsity", "parameter_change"]