全部版块 我的主页
论坛 计量经济学与统计论坛 五区 计量经济学与统计软件
2049 5
2010-06-11
Neural Network Design and the Complexity of Learning [Hardcover]
J. Stephen Judd (Author)





Editorial Reviews


Product Description


Using the tools of complexity theory, Stephen Judd develops a formal description of associative learning in connectionist networks. He rigorously exposes the computational difficulties in training neural networks and explores how certain design principles will or will not make the problems easier. Judd looks beyond the scope of any one particular learning rule, at a level above the details of neurons. There he finds new issues that arise when great numbers of neurons are employed and he offers fresh insights into design principles that could guide the construction of artificial and biological neural networks. The first part of the book describes the motivations and goals of the study and relates them to current scientific theory. It provides an overview of the major ideas, formulates the general learning problem with an eye to the computational complexity of the task, reviews current theory on learning, relates the book's model of learning to other models outside the connectionist paradigm, and sets out to examine scale-up issues in connectionist learning. Later chapters prove the intractability of the general case of memorizing in networks, elaborate on implications of this intractability and point out several corollaries applying to various special subcases. Judd refines the distinctive characteristics of the difficulties with families of shallow networks, addresses concerns about the ability of neural networks to generalize, and summarizes the results, implications, and possible extensions of the work. J. Stephen Judd is Visiting Assistant Professor of Computer Science at The California Institute of Technology. Neural Network Design and the Complexity of Learning is included in the Network Modeling and Connectionism series edited by Jeffrey Elman.






Product Details
  • Hardcover: 170 pages
  • Publisher: The MIT Press (April 6, 1990)
  • Language: English
  • ISBN-10: 0262100452
  • ISBN-13: 978-0262100458





附件列表
二维码

扫码加我 拉你入群

请注明:姓名-公司-职位

以便审核进群资格,未注明则拒绝

全部回复
2010-6-11 08:04:45
Neural Network Design and the Complexity of LearningProduct Code: 9780262100458
Format: Hardcover
Status: Instock (See Delivery Time for more details)
Condition: New

Annotation:Neurocomputing is a one-volume encyclopedic source of information on neural networks, an essential guide to the background of concepts taken from disciplines as varied as neuroscience, psychology, cognitive science, engineering, and physics.
Product Description:Using the tools of complexity theory, Stephen Judd develops a formal description of associative learning in connectionist networks. He rigorously exposes the computational difficulties in training neural networks and explores how certain design principles will or will not make the problems easier. Judd looks beyond the scope of any one particular learning rule, at a level above the details of neurons. There he finds new issues that arise when great numbers of neurons are employed and he offers fresh insights into design principles that could guide the construction of artificial and biological neural networks. The first part of the book describes the motivations and goals of the study and relates them to current scientific theory. It provides an overview of the major ideas, formulates the general learning problem with an eye to the computational complexity of the task, reviews current theory on learning, relates the book's model of learning to other models outside the connectionist paradigm, and sets out to examine scale-up issues in connectionist learning. Later chapters prove the intractability of the general case of memorizing in networks, elaborate on implications of this intractability and point out several corollaries applying to various special subcases. Judd refines the distinctive characteristics of the difficulties with families of shallow networks, addresses concerns about the ability of neural networks to generalize, and summarizes the results, implications, and possible extensions of the work. "Neural Network Design and the Complexity of Learning "is included in the Network Modeling and Connectionism series edited by Jeffrey Elman.

Product Attributes:
ISBN: 0262100452
ISBN-13: 9780262100458
Title: Neural Network Design and the Complexity of Learning
Authors: J. Stephen Judd
Format: Hardcover
Year: 1990
Publisher: MIT Press (MA)
Dimensions: 161mm x 17mm x 237mm
二维码

扫码加我 拉你入群

请注明:姓名-公司-职位

以便审核进群资格,未注明则拒绝

2010-6-11 08:25:30
多谢美女!
二维码

扫码加我 拉你入群

请注明:姓名-公司-职位

以便审核进群资格,未注明则拒绝

2010-6-12 08:13:41
正在研究网络
二维码

扫码加我 拉你入群

请注明:姓名-公司-职位

以便审核进群资格,未注明则拒绝

2011-11-11 08:57:52
谢谢楼主!欢迎研究复杂性经济学、非线性经济学、计算经济学、复杂经济系统和经济系统仿真的学人,到“复杂性经济学”交流群看看。群号:111688540。
二维码

扫码加我 拉你入群

请注明:姓名-公司-职位

以便审核进群资格,未注明则拒绝

2011-11-11 09:02:58
谢谢楼主!欢迎研究复杂性经济学、非线性经济学、计算经济学、复杂经济系统和经济系统仿真的学人,到“复杂性经济学”交流群看看。群号:111688540。
二维码

扫码加我 拉你入群

请注明:姓名-公司-职位

以便审核进群资格,未注明则拒绝

相关推荐
栏目导航
热门文章
推荐文章

说点什么

分享

扫码加好友,拉您进群
各岗位、行业、专业交流群