周鹏程，现任深圳理工大学生命健康学院智能交叉科学中心助理教授。中国科学技术大学物理学学士（2010），美国卡耐基梅隆大学神经计算与机器学习专业博士（2016），后在哥伦比亚大学统计系和计算神经科学中心从事博士后研究（2020）。

研究方向为生命科学与计算机的智能交叉，主要从事计算神经科学和机器学习/人工智能在脑科学中的应用，特别是大规模脑科学数据的统计建模和自动化分析处理。其关于钙荧光数据处理的一系列方法在领域内得到了广泛的应用。近期工作致力于开发与整合神经科学领域的一系列计算工具，打造完整的集大数据存储、传输、可视化、智能化处理和统计分析等于一体的自动化流程。论文发表在eLife，Nature Methods，Nature Neuroscience，Neuron，National Science Review等高影响因子杂志上，被引用4000余次。

Research Area

计算神经科学，机器学习，人工智能，数据科学，生物图像分析。

Research

Our lab focuses on Data Analysis, Modeling, and Intelligence to advance the understanding of neural systems through computational approaches. Collaborating closely with experimental neuroscientists, we explore a fundamental question: How do billions of dynamically interacting neurons give rise to intelligent behavior? Guided by David Marr’s "Three Levels of Analysis" framework, our research spans two interconnected directions:

• Computational Algorithms & Neural Representations：How do neural populations encode, transform, and decode behaviorally relevant information?

• Biological Implementations：How do circuit architectures physically realize these computations?

For decades, progress in these areas was limited by our inability to collect desired data at sufficient scale or resolution. This barrier has now been largely overcome through latest neurotechnologies. Today, we can simultaneously record thousands of neurons’ activity during behavior, and map the whole-brain connectomics at single-neuron resolution. However, these advances have created a new demand for analytical methods to bridge raw data to scientific understanding. As neural data scientists, we work closely with experimental neuroscientists to develop such methods, enabling us to address the core questions in system and circuit neuroscience.