For neural networks (NNs) with rectified linear unit (ReLU) or binary activation functions, we show that their training can be accomplished in a reduced parameter space. Specifically, the weights in each neuron can be trained on the unit sphere, as opposed to the entire space, and the threshold can be trained in a bounded interval, as opposed to the real line. We show that the NNs in the reduced parameter space are mathematically equivalent to the standard NNs with parameters in the whole space. The reduced parameter space shall facilitate the optimization procedure for the network training, as the search space becomes (much) smaller. We demonstrate the improved training performance using numerical examples.
翻译:对于具有校正线性单元或二进制激活功能的神经网络(NN),我们证明他们的训练可以在一个缩小的参数空间内完成。具体地说,每个神经元的重量可以在单位空间而不是整个空间内得到训练,而阈值可以在连接的间隔内得到训练,而不是在实际线内得到训练。我们显示,在缩小的参数空间内的NNP在数学上相当于标准NP,并带有整个空间的参数。随着搜索空间的缩小,减少的参数空间将便利网络培训的优化程序。我们用数字实例来展示培训绩效的改进。