首页>
外国专利>
Evolution of architectures for multitask neural networks
Evolution of architectures for multitask neural networks
展开▼
机译:多临时神经网络建筑的演变
展开▼
页面导航
摘要
著录项
相似文献
摘要
Evolution and coevolution of neural networks via multitask learning is described. The foundation is (1) the original soft ordering, which uses a fixed architecture for the modules and a fixed routing (i.e. network topology) that is shared among all tasks. This architecture is then extended in two ways with CoDeepNEAT: (2) by coevolving the module architectures (CM), and (3) by coevolving both the module architectures and a single shared routing for all tasks using (CMSR). An alternative evolutionary process (4) keeps the module architecture fixed, but evolves a separate routing for each task during training (CTR). Finally, approaches (2) and (4) are combined into (5), where both modules and task routing are coevolved (CMTR).
展开▼