Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2512.00619 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912773933367296 |
|---|---|
| author | Nalagatla, Goutham Grandhe, Shreyas |
| author_facet | Nalagatla, Goutham Grandhe, Shreyas |
| contents | Continual learning remains a fundamental challenge in artificial intelligence, with catastrophic forgetting posing a significant barrier to deploying neural networks in dynamic environments. Inspired by biological memory consolidation mechanisms, we propose a novel framework for generative replay that leverages predictive coding principles to mitigate forgetting. We present a comprehensive comparison between predictive coding-based and backpropagation-based generative replay strategies, evaluating their effectiveness on task retention and transfer efficiency across multiple benchmark datasets. Our experimental results demonstrate that predictive coding-based replay achieves superior retention performance (average 15.3% improvement) while maintaining competitive transfer efficiency, suggesting that biologically-inspired mechanisms can offer principled solutions to continual learning challenges. The proposed framework provides insights into the relationship between biological memory processes and artificial learning systems, opening new avenues for neuroscience-inspired AI research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_00619 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neuroscience-Inspired Memory Replay for Continual Learning: A Comparative Study of Predictive Coding and Backpropagation-Based Strategies Nalagatla, Goutham Grandhe, Shreyas Machine Learning Artificial Intelligence Continual learning remains a fundamental challenge in artificial intelligence, with catastrophic forgetting posing a significant barrier to deploying neural networks in dynamic environments. Inspired by biological memory consolidation mechanisms, we propose a novel framework for generative replay that leverages predictive coding principles to mitigate forgetting. We present a comprehensive comparison between predictive coding-based and backpropagation-based generative replay strategies, evaluating their effectiveness on task retention and transfer efficiency across multiple benchmark datasets. Our experimental results demonstrate that predictive coding-based replay achieves superior retention performance (average 15.3% improvement) while maintaining competitive transfer efficiency, suggesting that biologically-inspired mechanisms can offer principled solutions to continual learning challenges. The proposed framework provides insights into the relationship between biological memory processes and artificial learning systems, opening new avenues for neuroscience-inspired AI research. |
| title | Neuroscience-Inspired Memory Replay for Continual Learning: A Comparative Study of Predictive Coding and Backpropagation-Based Strategies |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2512.00619 |