Institute of Microelectronics, Tsinghua University, Beijing, China.
School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China.
PLoS One. 2019 Feb 22;14(2):e0212368. doi: 10.1371/journal.pone.0212368. eCollection 2019.
It is evident through biology research that, biological neural network could be implemented through two means: by congenital heredity, or by posteriority learning. However, traditionally, artificial neural network, especially the Deep learning Neural Networks (DNNs) are implemented only through exhaustive training and learning. Fixed structure is built, and then parameters are trained through huge amount of data. In this way, there are a lot of redundancies in the implemented artificial neural network. This redundancy not only requires more effort to train the network, but also costs more computing resources when used. In this paper, we proposed a bionic way to implement artificial neural network through construction rather than training and learning. The hierarchy of the neural network is designed according to analysis of the required functionality, and then module design is carried out to form each hierarchy. We choose the Drosophila's visual neural network as a test case to verify our method's validation. The results show that the bionic artificial neural network built through our method could work as a bionic compound eye, which can achieve the detection of the object and their movement, and the results are better on some properties, compared with the Drosophila's biological compound eyes.
很明显，通过生物学研究，生物神经网络可以通过两种方式实现：先天遗传或后天学习。然而，传统上，人工神经网络，特别是深度学习神经网络 (DNNs)，仅通过详尽的训练和学习来实现。建立固定的结构，然后通过大量数据训练参数。这样，在实现的人工神经网络中就会存在很多冗余。这种冗余不仅需要更多的精力来训练网络，而且在使用时还需要更多的计算资源。在本文中，我们提出了一种通过构建而不是通过训练和学习来实现人工神经网络的仿生方法。根据所需功能的分析来设计神经网络的层次结构，然后进行模块设计以形成每个层次结构。我们选择果蝇的视觉神经网络作为测试案例来验证我们方法的有效性。结果表明，通过我们的方法构建的仿生人工神经网络可以作为仿生复眼工作，可以实现对物体及其运动的检测，并且在某些特性上的结果优于果蝇的生物复眼。
