报 告 人：赵清宇 [斯坦福大学]

报告时间：2019年4月 15日（周一）报告10:00～10:30，讨论13:30～15:30

报告地点：乐乎一楼思源厅

主 持 人：冷拓

报告人简介：

赵清宇博士目前在斯坦福大学精神与行为科学学院从事博士后工作。他2012年于上海交通大学获得计算机学士学位，2017年于北卡罗来纳大学教堂山分校获得计算机博士学位。他的研究方向是使用新颖的图像分析与机器学习技术理解、诊断以及治疗精神类疾病。

报告摘要：

Generative models in combination with neural networks, such as variational autoencoders (VAE), have gained tremendous popularity in learning complex distribution of training data by embedding them into a low-dimensional latent space. For inference of the model, a traditional VAE often incorporates simple priors, e.g., a single Gaussian, for regularizing latent variables. This practice limits VAE’s modelling capacity when the target distribution is multi-modal. In this talk, I will present my recent work on exploring an extension of the VAE framework, by adopting robust mixture-models in the latent space, for the purpose of data clustering in the presence of outliers. Furthermore, reformulating basic VAEs often used for unsupervised learning, I propose a way to leverage them for general classification and regression tasks. I will show applications of such VAE-based frameworks in neuroimaging studies to understand how the brain structures change with age in both healthy aging and in neurodegenerative diseases, and also in discovering major patterns of functional brain connectivity.