论文标题
FOSTONN-基于Python的开源GPU用于操作神经网络
FastONN -- Python based open-source GPU implementation for Operational Neural Networks
论文作者
论文摘要
最近，已提出操作神经网络（ONNS）作为网格结构数据的特殊人工神经网络。它们使异源非线性操作能够推广广泛采用的基于卷积的神经元模型。这项工作介绍了一个快速支持GPU的库，用于培训操作神经网络Fostonn，该库基于操作神经元的新型矢量化表述。在利用自动反向模式分化以进行反向传播的情况下，Fostonn可以通过合并新操作员组和自定义梯度流的融合来提高灵活性。此外，捆绑的辅助模块还提供了跨不同数据分区和自定义指标的性能跟踪和检查点的接口。
Operational Neural Networks (ONNs) have recently been proposed as a special class of artificial neural networks for grid structured data. They enable heterogenous non-linear operations to generalize the widely adopted convolution-based neuron model. This work introduces a fast GPU-enabled library for training operational neural networks, FastONN, which is based on a novel vectorized formulation of the operational neurons. Leveraging on automatic reverse-mode differentiation for backpropagation, FastONN enables increased flexibility with the incorporation of new operator sets and customized gradient flows. Additionally, bundled auxiliary modules offer interfaces for performance tracking and checkpointing across different data partitions and customized metrics.
