I am a final year Ph.D. student in the joint program between the Neuroscience Institute 🧠 and the Machine Learning Department. I am fortunate to be advised by Prof. Byron Yu, Prof. Matthew Smith, and Prof. Brent Doiron. My main research topic is machine learning algorithms for optimizing spiking network models to generate realistic neuronal activity. I have also worked with Prof. Leila Wehbe and Prof. Aaditya Ramdas on individual identification and privacy in brain recordings, and Prof. Woody Zhu on generative models and causal inference.

Before coming to CMU, I obtained a bachelor’s degree in mathematics and statistics from Columbia University, where I worked with Prof. Liam Paninski on a machine learning pipeline for neural signal processing. I have also spent two wonderful years in Hong Kong, where I studied computing mathematics at City University of Hong Kong, before enrolling in the joint bachelor’s degree program between CityU and Columbia.

Education

Ph.D. in Neural Computation and Machine Learning, Carnegie Mellon University, 2018-2023 (expected in Dec)

Thesis committee: Byron Yu, Matthew Smith, Brent Doiron, Chengcheng Huang, Robert Kass, Tatiana Engel

B.A. in Mathematics-Statistics, Columbia University, 2015-2018

B.S. in Computing Mathematics, City University of Hong Kong, 2013-2015

Work Experience

Research Scientist Intern, Applied Machine Learning Group, Tiktok (ByteDance), 2022
Developed a reinforcement learning framework based on graph neural networks to accelerate molecular simulation.

Research Interests

My research interests lie at the intersection of machine learning and neuroscience. I work closely with experimentalists and develop machine learning tools to study the neuronal mechanisms of brain function. I have developed statistical and machine learning methods using generative models, spiking neural networks, Bayesian optimization, and reinforcement learning. Besides neuroscience, I have also worked on projects with applications in health care and scientific computing.

Journal Publications and preprints

📄 Automated customization of large-scale spiking network models to neuronal population activity. (Under review) Paper
Shenghao Wu, Chengcheng Huang, Adam Snyder, Matthew Smith, Brent Doiron, Byron Yu
Keywords: Bayesian optimization, dimensionality reduction, spiking neural networks, brain-computer interface.

📄 Brainprints: identifying individuals from magnetoencephalograms. (Communications Biology 2022) Paper Code
Shenghao Wu, Aaditya Ramdas, Leila Wehbe
Keywords: neuroimaging, privacy, feature engineering, multi-modal recordings.

📄 YASS: Yet Another Spike Sorter applied to large-scale multi-electrode array recordings in primate retina. (In submission) Paper Code
JinHyung Lee, Catalin Mitelut, Hooshmand Shokri, Ian Kinsella, Nishchal Dethe, Shenghao Wu, Kevin Li, Eduardo Blancas Reyes, Denis Turcu, Eleanor Batty, Young Joon Kim, Nora Brackbill, Alexandra Kling, Georges Goetz, E.J. Chichilnisky, David Carlson, Liam Paninski
Keywords: signal processing, convolutional neural networks, generative models, spike sorting.

Conference Publications and presentations

📄 Counterfactual Generative Models for Time-Varying Treatments. (Spotlight, Deep Generative Models for Health (DGM4H) Workshop at NeurIPS 2023; Full paper under review at ICLR 2024.) Paper
Shenghao Wu, Wenbin Zhou, Minshuo Chen, Shixiang Zhu
Keywords: generative models, causal inference, time series, counterfactual prediction.

📄 Interpreting area-to-area differences in spiking variability using spiking network models. (Society for Neuroscience, 2023)
Shenghao Wu, Adam Snyder, Chengcheng Huang, Matthew Smith, Byron Yu, Brent Doiron
Keywords: deep neural emulators, mechanistic models.

📄 RLCG: When Reinforcement Learning Meets Coarse Graining. (Neurips AI4Science Workshop 2022) Paper
Shenghao Wu, Tianyi Liu, Zhirui Wang, Wen Yan, Yingxiang Yang
Keywords: graph neural networks, reinforcement learning, molecular dynamics.

📄 Automatic fitting of spiking network models to neuronal activity reveals limits of model flexibility. (Computational and Systems Neuroscience, 2020) Abstract
Shenghao Wu, Chengcheng Huang, Adam Snyder, Matthew Smith, Brent Doiron, Byron Yu

📄 Neural networks for sorting neurons. (Computational and Systems Neuroscience, 2020) Abstract
JinHyung Lee, Catalin Mitelut, Ian Kinsella, Shenghao Wu, Eleanor Batty, Liam Paninski, Hooshmand Shokri, Ari Pakman, Yueqi Wang, Nishchal Dethe, Kevin Li, Eduardo Blancas Reyes, Alexandra Tikidji-Hamburyan, Georges Goetz, Ej Chichilnisky, David Carlson

📄 Riskalyzer: Inferring Individual Risk-Taking Propensity Using Phone Metadata. (ACM Ubicomp 2018) Paper
Vivek Singh, Rushil Goyal, Shenghao Wu

Services

PC Member: Neurips AI4Science Workshop (2023), Neurips Generative AI & Biology Workshop (2023), KDD (2023), Brain Informatics (2023), ACAIN (2021, 2022, 2023)
Journal Reviewer : Information Fusion