Reliable and fast recurrent neural network architecture optimization
This article introduces Random Error Sampling-based Neuroevolution (RESN), a novel
automatic method to optimize recurrent neural network architectures. RESN combines an
evolutionary algorithm with a training-free evaluation approach. The results show that RESN
achieves state-of-the-art error performance while reducing by half the computational time.
automatic method to optimize recurrent neural network architectures. RESN combines an
evolutionary algorithm with a training-free evaluation approach. The results show that RESN
achieves state-of-the-art error performance while reducing by half the computational time.
This article introduces Random Error Sampling-based Neuroevolution (RESN), a novel automatic method to optimize recurrent neural network architectures. RESN combines an evolutionary algorithm with a training-free evaluation approach. The results show that RESN achieves state-of-the-art error performance while reducing by half the computational time.
arxiv.org
以上显示的是最相近的搜索结果。 查看全部搜索结果