Since the machine learning techniques are improving rapidly, it has been shown that the image recognition techniques in deep neural networks can be used to detect jet substructure. And it turns out that deep neural networks can match or outperform traditional approach of expert features. However, there are disadvantages such as sparseness of jet images. Based on the natural tree-like structure of jet sequential clustering, the recursive neural networks (RecNNs), which embed jet clustering history recursively as in natural language processing, have a better behavior when confronted with these problems. We thus try to explore the performance of RecNN in quark/gluon discrimination. In order to indicate the realistic potential at the LHC, We include the detector simulation in our data preparation. We attempt to implement particle flow identification in one-hot vectors or using instead a recursively defined pt-weighted charge. The results show that RecNNs work better than the baseline BDT by a few percent in gluon rejection at the working point of 50\% quark acceptance. However, extra implementation of particle flow identification only increases the performance slightly. We also experimented on some relevant aspects which might influence the performance of networks. It shows even only particle flow identification as input feature without any extra information on momentum or angular position is already giving a fairly good result, which indicates that most of the information for q/g discrimination is already included in the tree-structure itself. As a bonus, a rough u/d discrimination is also explored.
View on arXiv