Three different Artificial Neural Network architectures have been applied to perform neutron/$\gamma$ discrimination in neda based on waveform and time-of-flight information. Using the coincident $\gamma$-rays from agata, we have been able to measure and compare on real data the performances of the Artificial Neural Networks as classifiers. While the general performances are quite similar for the data set we used, differences, in particular related to the computing times, have been highlighted. One of the Artificial Neural Network architecture has also been found more robust to time misalignment of the waveforms. Such a feature is of great interest for online processing of waveforms.

三种不同的人工神经网络架构已应用于执行中子/$\gamma$基于波形和飞行时间信息的neda识别。使用巧合$\gamma$从Agata发出的X射线，我们已经能够测量和比较真实数据作为分类器的人工神经网络的性能。尽管我们使用的数据集的总体性能非常相似，但差异尤其是与计算时间有关的差异已得到突出显示。还发现一种人工神经网络体系结构对波形的时间未对准更健壮。对于波形的在线处理，这种功能非常有用。