This paper introduces a novel deep learning based method, named bridge neural network (BNN) to dig the potential relationship between two given data sources task by task. The proposed approach employs two convolutional neural networks that project the two data sources into a feature space to learn the desired common representation required by the specific task. The training objective with artificial negative samples is introduced with the ability of mini-batch training and it's asymptotically equivalent to maximizing the total correlation of the two data sources, which is verified by the theoretical analysis. The experiments on the tasks, including pair matching, canonical correlation analysis, transfer learning, and reconstruction demonstrate the state-of-the-art performance of BNN, which may provide new insights into the aspect of common representation learning.

本文介绍了一种基于深度学习的新型方法——桥接神经网络（BNN），用于针对特定任务挖掘两个给定数据源之间的潜在关系。该方法采用两个卷积神经网络将两个数据源投影到特征空间中，学习特定任务所需的所需的共同表示。训练目标是介绍人工负样本的能力，使得小批量训练的抗性等价于最大化两个数据源的总相关性，并通过理论分析进行了验证。在配对、典型相关分析、迁移学习和重构等任务上的实验表明，BNN具有最先进的性能，可能为共同表示学习方面带来新的见解。

通过桥接神经网络进行任务驱动的公共表示学习