您现在的位置是：首页 > 技术资料 > 神经网络与深度学习综述DeepLearning

推荐星级：

神经网络与深度学习综述DeepLearning

更新时间：2019-11-13 10:54:16 大小：266K 上传用户：xuzhen1 查看TA发布的资源 标签：神经网络深度 deep learning 下载积分：0分评价赚积分（如何评价?）收藏评论(0) 举报

资料介绍

Preface This is the draft of an invited Deep Learning(DL) overview. One of its goals is to assign credit to those who contributed to the present state of the art.I acknowledge the limitations of attempting to achieve this goal. The DL research community itself may be viewed as a continually evolving, deep network of scientists who have in? uenced each other in complex ways. Starting from recent DL results,I tried to traceback the origins of relevant ideas through the past half century and beyond, sometimes using "locasearch "

to follow citations of citations backwards in time. Since not all DL publications properly acknowledge earlier relevant work, additional global search strategies were employed, aided by consulting numerous neural network experts. As a result, the present draft mostly consists of references(about 800 entries so far). Nevertheless, through an expert selection bias I may have missed important work.A related bias was surely introduced by my special familiarity with the work of my own DL research group in the past quarter-century. For these reasons, the present draft should be viewed as merely a snapshot of an ongoing credit assignment process. To help improve it, please do not hesitate to send corrections and suggestions to juergen@ idsia. ch.

部分文件列表

文件名	大小
神经网络与深度学习综述DeepLearning.pdf	266K

立即下载

【关注视频号领20积分】【关注公众号立即送20积分】

部分页面预览

（完整内容请下载后查看）

Draft: Deep Learning in Neural Networks: An Overview

Technical Report IDSIA-03-14 / arXiv:1404.7828 (v1.5) [cs.NE]

Ju¨rgen Schmidhuber

The Swiss AI Lab IDSIA

Istituto Dalle Molle di Studi sull ’ IntelligenzAarti?ciale

University of Lugano & SUPSI

Galleria 2, 6928 Manno-Lugano

Switzerland

15 May 2014

Abstract

In recent years, deep arti?cial neural networks (including recurrent ones) have won numerous con-

testsin pattern recognition and machine learning. This historical surveycompactly summarisesrelevant

work, much of it from the previous millennium. Shallow and deep learners are distinguished by the

depth of their credit assignment paths, which are chains of possibly learnable, causal links between ac-

tions and effects. I review deep supervised learning (also recapitulating the history of backpropagation),

unsupervisedlearning, reinforcement learning & evolutionary computation, and indirect searchfor short

programs encoding deepand large networks.

^～juergen/DeepLearning30April2014.pdf

^～juergen/DeepLearning30April2014.tex

PDF of earlier draft (v1): http://www.idsia.ch/

LATEX source:

^～juergen/bib.bib

Complete BIBTEX ?le: http://www.idsia.ch/

Preface

This is the draft of an invited Deep Learning (DL) overview. One of its goals is to assign credit to those

who contributed to the present state of the art. I acknowledge the limitations of attempting to achieve

this goal. The DL research community itself may be viewed as a continually evolving, deep network of

scientists who have in?uenced each other in complex ways. Starting from recent DL results, I tried to trace

back the origins of relevant ideas through the past half century and beyond, sometimes using “ locasl earch ”

to follow citations of citations backwards in time. Since not all DL publications properly acknowledge

earlier relevant work, additional global search strategies were employed, aided by consulting numerous

neural network experts. As a result, the present draft mostly consists of references (about 800 entries so

far). Nevertheless, through an expert selection bias I may have missed important work. A related bias

was surely introduced by my special familiarity with the work of my own DL research group in the past

quarter-century. For these reasons, the present draft should be viewed as merely a snapshot of an ongoing

credit assignment process. To help improve it, please do not hesitate to send corrections and suggestions to

全部评论(0)

暂无评论

评论赚积分>>

上传资源

神经网络与深度学习综述DeepLearning

资料介绍

部分文件列表

部分页面预览

相关下载

全部评论(0)

热门标签

最新上传

热门下载

推荐下载

专栏首页