五分彩APP

首 页机构概况机构设置科研人才队伍合作交流研究生教育博士后创新文化党群园地院重点实验室彭桓武中心信息公开
  学术活动
  您现在的位置:五分彩APP > 学术活动 > 专题学术报告/Seminar
A Short Tutorial on Convolutional Neural Networks and Recurrent Neural Networks
2019-06-03  【 】【打印】【关闭

CAS Key Laboratory of Theoretical Physics

Institute of Theoretical Physics

Chinese Academy of Sciences

Seminar

Title

题目

A Short Tutorial on Convolutional Neural Networks and Recurrent Neural Networks

Speaker

报告人

朱占星

Affiliation

所在单位

北京大学数学科学学院

Date

日期

2019年6月3日(周一)上午9:00
 

Venue

地点

6420 ITP South Building

Abstract

摘要

In this tutorial, I will elaborate two powerful deep learning models, Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), particularly suitable for modeling image and sequence data, respectively. I will introduce their architectures, the design principle and difficulties of training. Some variants will be introduced, such as ResNet, DenseNet, Long-Short Memory Network (LSTM), attention mechanism, etc. Various examples will be provided and analyzed as well.

Contact Person

所内联系人

Pan Zhang
IE6.0浏览器,1024X768分辨率 版权所有 © 中国科学院理论物理研究所
地址:北京市海淀区中关村东路55号 邮政编码:100190
【】 京公网安备1101080094号