资源分类
》 资源 》论文》Self-Organizing Incremental Neural Networks for Continual Learning

Self-Organizing Incremental Neural Networks for Continual Learning

2019-10-11 | |  94 |   42 |   0
Abstract Continual learning systems can adapt to new tasks, changes in data distributions, and new information that becomes incrementally available over time. The key challenge for such systems is how to mitigate catastrophic forgetting, i.e., how to prevent the loss of previously learned knowledge when new tasks need to be solved. In our research, we investigate self-organizing incremental neural networks (SOINN) for continual learning from both stationary and non-stationary data. We have developed a new algorithm, SOINN+, that learns to forget irrelevant nodes and edges and is robust to noise

上一篇：OpenMarkov, an Open-Source Tool for Probabilistic Graphical Models

下一篇：The Open Vault Challenge - Learning How to Build Calibration-Free Interactive Systems by Cracking the Code of a Vault

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...