Novel interpretable mechanism of neural networks based on network decoupling method

The lack of interpretability of the neural network algorithm has become the bottleneck of its wide application. We propose a general mathematical framework, which couples the complex structure of the system with the nonlinear activation function to explore the decoupled dimension reduction method of high-dimensional system and reveal the calculation mechanism of the neural network. We apply our framework to some network models and a real system of the whole neuron map of Caenorhabditis elegans. Result shows that a simple linear mapping relationship exists between network structure and network behavior in the neural network with high-dimensional and nonlinear characteristics. Our simulation and theoretical results fully demonstrate this interesting phenomenon. Our new interpretation mechanism provides not only the potential mathematical calculation principle of neural network but also an effective way to accurately match and predict human brain or animal activities, which can further expand and enrich the interpretable mechanism of artificial neural network in the future.

Automated summary

The lack of interpretability of neural network algorithm has become a bottleneck for its wide application. The article proposes a general mathematical framework that couples the complex structure of the system with the nonlinear activation function to explore the dimension reduction method of high-dimensional system and reveal the calculation mechanism of the neural network. Results show a linear mapping relationship between network structure and behavior in high-dimensional and nonlinear neural networks.