网站地图 | 联系我们 | English | 意见反馈 | 主任信箱
 
首页 中心概况 新闻动态 科研进展 交流合作 人才培养 研究队伍 人才招聘 政策规章 数学交叉科学传播
学术报告
现在位置:首页 > 学术报告

Recent Advances in Autoregressive Density Estimation with Deep Neural Networks
【2017.11.10 10:00am, N420】

【打印】【关闭】

 2017-11-01 

  Colloquia & Seminars 

  Speaker

Scott Reed, Research Scientist, Deepmind 

  Title

Recent Advances in Autoregressive Density Estimation with Deep Neural Networks

  Time

11月10日(星期五)上午 10:00-11:30

  Venue

N420

  Abstract

Autoregressive models parametrized as deep neural networks  (called
PixelCNN) achieve state-of-the-art results in image density estimation.
Although training is fast, sampling is costly, requiring one network
evaluation per pixel; O(N) for N pixels. In this talk, I will describe a
parallelized PixelCNN that  achieves competitive density estimation and
orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling
the practical generation of high-resolution images. Results will be
presented on class-conditional image generation, text-to-image synthesis,
and action-conditional video generation. In the second part of the talk, I
will discuss density estimation in the low-data regime as a meta learning
problem.  

  Affiliation

Scott is a research scientist at DeepMind. He completed his PhD
with Honglak Lee at the University of Michigan in 2016. His research focuses
on deep learning methods for image generation, object detection, imitation
learning and program induction.  

欢迎访问国家数学与交叉科学中心 
地址:北京海淀区中关村东路55号 邮编:100190 电话: 86-10-62613242 Fax: 86-10-62616840 邮箱: ncmis@amss.ac.cn