Dr. Xiwei She is a postdoctoral scholar in the Department of Neurology. He received his B.S. degree in Computer Science from Shanghai Jiao Tong University in 2013, and his M.S. degree in Biomedical Engineering from Zhejiang University in 2016. Worked as a research assistant at the USC Neural Modeling and Interface Laboratory, he received his Ph.D. degree in Biomedical Engineering from the University of Southern California in 2022. After graduation, he joined Stanford University as a postdoctoral scholar at the Pediatric Neurostimulation Laboratory (Baumer Lab) and Wu Tsai Neuroscience Institute.
His research interests are largely directed toward identifying the causal relationship of neurons/brain regions and understanding how information is encoded in neural signals by employing machine learning models. Specifically, his postdoc research focuses on applying machine learning modeling techniques on EEG and TMS-EEG data to better understand the impact of interictal epileptiform discharges (IEDs) on brain activity in children with childhood epilepsy with centrotemporal spikes (CECTS).

Stanford Advisors

Lab Affiliations

All Publications

  • Accelerating input-output model estimation with parallel computing for testing hippocampal memory prostheses in human JOURNAL OF NEUROSCIENCE METHODS She, X., Robinson, B., Flynn, G., Berger, T. W., Song, D. 2022; 370: 109492


    Hippocampal memory prosthesis is defined as a closed-loop biomimetic system that can be used for restoration and enhancement of memory functions impaired in diseases or injuries. To build such a prosthesis, we have developed two types of input-output models, i.e., a multi-input multi-output (MIMO) model for predicting output spike trains based on input spikes, and a double-layer multi-resolution memory decoding (MD) model for classifying spatio-temporal patterns of spikes into memory categories. Both models can achieve high prediction accuracy using human hippocampal spikes data and can be used to derive electrical stimulation patterns to test the hippocampal memory prosthesis.However, testing hippocampal memory prostheses in human epilepsy patients with such models has to be performed within a much shorter time window (48-72 h) due to clinical limitations. To solve this problem, we have developed parallelization strategies to decompose the overall model estimation task into multiple independent sub-tasks involving different outputs and cross-validation folds. These sub-tasks are then accomplished in parallel on different computer nodes to reduce model estimation time.Implementing both parallel schemes with a high-performance computer cluster, we successfully reduced the computing time of model estimations from hundreds of hours to tens of hours.We have tested the two parallel computing schemes for both MIMO and MD models with data collected from 11 human subjects. The performances of the parallel schemes are compared with the performance of the non-parallel scheme.Such strategies allow us to complete the modeling procedure within the required time frame to further test input-output model-driven electrical stimulations for the hippocampal memory prosthesis. It has important implications to test the model-based DBS intraoperatively and developing clinically viable hippocampal memory prostheses.

    View details for DOI 10.1016/j.jneumeth.2022.109492

    View details for Web of Science ID 000788139600003

    View details for PubMedID 35104492

  • A Double-Layer Multi-Resolution Classification Model for Decoding Spatiotemporal Patterns of Spikes With Small Sample Size NEURAL COMPUTATION She, X., Berger, T. W., Song, D. 2021; 34 (1): 219-254


    We build a double-layer, multiple temporal-resolution classification model for decoding single-trial spatiotemporal patterns of spikes. The model takes spiking activities as input signals and binary behavioral or cognitive variables as output signals and represents the input-output mapping with a double-layer ensemble classifier. In the first layer, to solve the underdetermined problem caused by the small sample size and the very high dimensionality of input signals, B-spline functional expansion and L1-regularized logistic classifiers are used to reduce dimensionality and yield sparse model estimations. A wide range of temporal resolutions of neural features is included by using a large number of classifiers with different numbers of B-spline knots. Each classifier serves as a base learner to classify spatiotemporal patterns into the probability of the output label with a single temporal resolution. A bootstrap aggregating strategy is used to reduce the estimation variances of these classifiers. In the second layer, another L1-regularized logistic classifier takes outputs of first-layer classifiers as inputs to generate the final output predictions. This classifier serves as a meta-learner that fuses multiple temporal resolutions to classify spatiotemporal patterns of spikes into binary output labels. We test this decoding model with both synthetic and experimental data recorded from rats and human subjects performing memory-dependent behavioral tasks. Results show that this method can effectively avoid overfitting and yield accurate prediction of output labels with small sample size. The double-layer, multi-resolution classifier consistently outperforms the best single-layer, single-resolution classifier by extracting and utilizing multi-resolution spatiotemporal features of spike patterns in the classification.

    View details for DOI 10.1162/neco_a_01459

    View details for Web of Science ID 000730790000008

    View details for PubMedID 34758485

    View details for PubMedCentralID PMC9470026