Abstract Neural Architecture Search (NAS) was first proposed to achieve state-of-the-art
performance through the discovery of new architecture patterns, without human intervention …

To address the challenges related to segmentation complexity, high memory usage,
extended training duration, and low equipment utilization in parallel optimization of large …

With the proposal of neural architecture search (NAS), automated network architecture
design gradually becomes a new way in deep learning research. Due to its high capability …

为解决传统手工切分神经网络模型计算任务并行化方法面临的并行化难度大, 训练耗时长,
设备利用率低等问题, 提出了一种基于深度神经网络(DNN) 模型特性感知的任务切分及并行优化 …

In order to solve the problems of difficult parallelization, long training time, and low
equipment utilization in the traditional parallelization method of manually partitioning …

One practice of employing deep neural networks is to apply the same architecture to all the
input instances. However, a fixed architecture may not be representative enough for data …

Transfer learning research attempts to make model induction transferable across different
domains. This method assumes that specific information regarding to which domain each …