论文标题
将神经网络参数初始化减少为SMT问题
Reducing Neural Network Parameter Initialization Into an SMT Problem
论文作者
论文摘要
训练神经网络（NN）取决于多种因素，包括但不限于初始权重。在本文中，我们专注于初始化深NN参数，以使其性能更好，与随机或零初始化相比。我们通过将初始化的过程减少到SMT求解器来做到这一点。先前的作品考虑了在小NN上的某些激活功能，但是所研究的NN是具有不同激活函数的深层网络。我们的实验表明，与随机初始化的网络相比，参数初始化的提出的方法可以实现更好的性能。
Training a neural network (NN) depends on multiple factors, including but not limited to the initial weights. In this paper, we focus on initializing deep NN parameters such that it performs better, comparing to random or zero initialization. We do this by reducing the process of initialization into an SMT solver. Previous works consider certain activation functions on small NNs, however the studied NN is a deep network with different activation functions. Our experiments show that the proposed approach for parameter initialization achieves better performance comparing to randomly initialized networks.
