Atjaunināt sīkdatņu piekrišanu

E-grāmata: Meta-Algorithmics: Patterns for Robust, Low Cost, High Quality Systems

3.50/5 (4 ratings by Goodreads)
  • Formāts: PDF+DRM
  • Sērija : IEEE Press
  • Izdošanas datums: 28-May-2013
  • Izdevniecība: Wiley-IEEE Press
  • Valoda: eng
  • ISBN-13: 9781118626702
Citas grāmatas par šo tēmu:
  • Formāts - PDF+DRM
  • Cena: 102,25 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Ielikt grozā
  • Pievienot vēlmju sarakstam
  • Šī e-grāmata paredzēta tikai personīgai lietošanai. E-grāmatas nav iespējams atgriezt un nauda par iegādātajām e-grāmatām netiek atmaksāta.
  • Bibliotēkām
Meta-Algorithmics: Patterns for Robust, Low Cost, High Quality SystemsPalielināt
  • Formāts: PDF+DRM
  • Sērija : IEEE Press
  • Izdošanas datums: 28-May-2013
  • Izdevniecība: Wiley-IEEE Press
  • Valoda: eng
  • ISBN-13: 9781118626702
Citas grāmatas par šo tēmu:

DRM restrictions

  • Kopēšana (kopēt/ievietot):

    nav atļauts

  • Drukāšana:

    nav atļauts

  • Lietošana:

    Digitālo tiesību pārvaldība (Digital Rights Management (DRM))
    Izdevējs ir piegādājis šo grāmatu šifrētā veidā, kas nozīmē, ka jums ir jāinstalē bezmaksas programmatūra, lai to atbloķētu un lasītu. Lai lasītu šo e-grāmatu, jums ir jāizveido Adobe ID. Vairāk informācijas šeit. E-grāmatu var lasīt un lejupielādēt līdz 6 ierīcēm (vienam lietotājam ar vienu un to pašu Adobe ID).

    Nepieciešamā programmatūra
    Lai lasītu šo e-grāmatu mobilajā ierīcē (tālrunī vai planšetdatorā), jums būs jāinstalē šī bezmaksas lietotne: PocketBook Reader (iOS / Android)

    Lai lejupielādētu un lasītu šo e-grāmatu datorā vai Mac datorā, jums ir nepieciešamid Adobe Digital Editions (šī ir bezmaksas lietotne, kas īpaši izstrādāta e-grāmatām. Tā nav tas pats, kas Adobe Reader, kas, iespējams, jau ir jūsu datorā.)

    Jūs nevarat lasīt šo e-grāmatu, izmantojot Amazon Kindle.

The confluence of cloud computing, parallelism and advanced machine intelligence approaches has created a world in which the optimum knowledge system will usually be architected from the combination of two or more knowledge-generating systems. There is a need, then, to provide a reusable, broadly-applicable set of design patterns to empower the intelligent system architect to take advantage of this opportunity.

This book explains how to design and build intelligent systems that are optimized for changing system requirements (adaptability), optimized for changing system input (robustness), and optimized for one or more other important system  parameters (e.g., accuracy, efficiency, cost). It provides an overview of traditional parallel processing which is shown to consist primarily of task and component parallelism; before introducing meta-algorithmic parallelism which is based on combining two or more algorithms, classification engines or other systems.

Key features:





Explains the entire roadmap for the design, testing, development, refinement, deployment and statistics-driven optimization of building systems for intelligence Offers an accessible yet thorough overview of machine intelligence, in addition to having a strong image processing focus Contains design patterns for parallelism, especially meta-algorithmic parallelism simply conveyed, reusable and proven effective that can be readily included in the toolbox of experts in analytics, system architecture, big data, security and many other science and engineering disciplines Connects algorithms and analytics to parallelism, thereby illustrating a new way of designing intelligent systems compatible with the tremendous changes in the computing world over the past decade Discusses application of the approaches to a wide number of fields; primarily, document understanding, image understanding, biometrics and security printing Companion website contains sample code and data sets
Acknowledgments xi
1 Introduction and Overview
1(41)
1.1 Introduction
1(1)
1.2 Why Is This Book Important?
2(1)
1.3 Organization of the Book
3(1)
1.4 Informatics
4(2)
1.5 Ensemble Learning
6(1)
1.6 Machine Learning/Intelligence
7(15)
1.6.1 Regression and Entropy
8(1)
1.6.2 SVMs and Kernels
9(6)
1.6.3 Probability
15(2)
1.6.4 Unsupervised Learning
17(1)
1.6.5 Dimensionality Reduction
18(2)
1.6.6 Optimization and Search
20(2)
1.7 Artificial Intelligence
22(9)
1.7.1 Neural Networks
22(3)
1.7.2 Genetic Algorithms
25(3)
1.7.3 Markov Models
28(3)
1.8 Data Mining/Knowledge Discovery
31(1)
1.9 Classification
32(6)
1.10 Recognition
38(1)
1.11 System-Based Analysis
39(1)
1.12 Summary
39(3)
References
40(2)
2 Parallel Forms of Parallelism
42(31)
2.1 Introduction
42(1)
2.2 Parallelism by Task
43(9)
2.2.1 Definition
43(3)
2.2.2 Application to Algorithms and Architectures
46(5)
2.2.3 Application to Scheduling
51(1)
2.3 Parallelism by Component
52(12)
2.3.1 Definition and Extension to Parallel-Conditional Processing
52(3)
2.3.2 Application to Data Mining, Search, and Other Algorithms
55(4)
2.3.3 Application to Software Development
59(5)
2.4 Parallelism by Meta-algorithm
64(7)
2.4.1 Meta-algorithmics and Algorithms
66(1)
2.4.2 Meta-algorithmics and Systems
67(1)
2.4.3 Meta-algorithmics and Parallel Processing
68(1)
2.4.4 Meta-algorithmics and Data Collection
69(1)
2.4.5 Meta-algorithmics and Software Development
70(1)
2.5 Summary
71(2)
References
72(1)
3 Domain Areas: Where Are These Relevant?
73(31)
3.1 Introduction
73(1)
3.2 Overview of the Domains
74(1)
3.3 Primary Domains
75(11)
3.3.1 Document Understanding
75(2)
3.3.2 Image Understanding
77(1)
3.3.3 Biometrics
78(1)
3.3.4 Security Printing
79(7)
3.4 Secondary Domains
86(15)
3.4.1 Image Segmentation
86(4)
3.4.2 Speech Recognition
90(1)
3.4.3 Medical Signal Processing
90(2)
3.4.4 Medical Imaging
92(3)
3.4.5 Natural Language Processing
95(2)
3.4.6 Surveillance
97(1)
3.4.7 Optical Character Recognition
98(3)
3.4.8 Security Analytics
101(1)
3.5 Summary
101(3)
References
102(2)
4 Applications of Parallelism by Task
104(33)
4.1 Introduction
104(1)
4.2 Primary Domains
105(30)
4.2.1 Document Understanding
112(6)
4.2.2 Image Understanding
118(8)
4.2.3 Biometrics
126(5)
4.2.4 Security Printing
131(4)
4.3 Summary
135(2)
References
136(1)
5 Application of Parallelism by Component
137(38)
5.1 Introduction
137(1)
5.2 Primary Domains
138(34)
5.2.1 Document Understanding
138(14)
5.2.2 Image Understanding
152(10)
5.2.3 Biometrics
162(8)
5.2.4 Security Printing
170(2)
5.3 Summary
172(3)
References
173(2)
6 Introduction to Meta-algorithmics
175(66)
6.1 Introduction
175(3)
6.2 First-Order Meta-algorithmics
178(17)
6.2.1 Sequential Try
178(3)
6.2.2 Constrained Substitute
181(3)
6.2.3 Voting and Weighted Voting
184(5)
6.2.4 Predictive Selection
189(3)
6.2.5 Tessellation and Recombination
192(3)
6.3 Second-Order Meta-algorithmics
195(23)
6.3.1 Confusion Matrix and Weighted Confusion Matrix
195(4)
6.3.2 Confusion Matrix with Output Space Transformation (Probability Space Transformation)
199(4)
6.3.3 Tessellation and Recombination with Expert Decisioner
203(3)
6.3.4 Predictive Selection with Secondary Engines
206(2)
6.3.5 Single Engine with Required Precision
208(1)
6.3.6 Majority Voting or Weighted Confusion Matrix
209(1)
6.3.7 Majority Voting or Best Engine
210(2)
6.3.8 Best Engine with Differential Confidence or Second Best Engine
212(5)
6.3.9 Best Engine with Absolute Confidence or Weighted Confusion Matrix
217(1)
6.4 Third-Order Meta-algorithmics
218(22)
6.4.1 Feedback
219(2)
6.4.2 Proof by Task Completion
221(3)
6.4.3 Confusion Matrix for Feedback
224(4)
6.4.4 Expert Feedback
228(4)
6.4.5 Sensitivity Analysis
232(4)
6.4.6 Regional Optimization (Extended Predictive Selection)
236(3)
6.4.7 Generalized Hybridization
239(1)
6.5 Summary
240(1)
References
240(1)
7 First-Order Meta-algorithmics and Their Applications
241(31)
7.1 Introduction
241(1)
7.2 First-Order Meta-algorithmics and the "Black Box"
241(1)
7.3 Primary Domains
242(15)
7.3.1 Document Understanding
242(4)
7.3.2 Image Understanding
246(6)
7.3.3 Biometrics
252(4)
7.3.4 Security Printing
256(1)
7.4 Secondary Domains
257(14)
7.4.1 Medical Signal Processing
258(6)
7.4.2 Medical Imaging
264(4)
7.4.3 Natural Language Processing
268(3)
7.5 Summary
271(1)
References
271(1)
8 Second-Order Meta-algorithmics and Their Applications
272(38)
8.1 Introduction
272(1)
8.2 Second-Order Meta-algorithmics and Targeting the "Fringes"
273(6)
8.3 Primary Domains
279(25)
8.3.1 Document Understanding
280(13)
8.3.2 Image Understanding
293(4)
8.3.3 Biometrics
297(2)
8.3.4 Security Printing
299(5)
8.4 Secondary Domains
304(4)
8.4.1 Image Segmentation
305(2)
8.4.2 Speech Recognition
307(1)
8.5 Summary
308(2)
References
308(2)
9 Third-Order Meta-algorithmics and Their Applications
310(32)
9.1 Introduction
310(1)
9.2 Third-Order Meta-algorithmic Patterns
311(2)
9.2.1 Examples Covered
311(1)
9.2.2 Training-Gap-Targeted Feedback
311(2)
9.3 Primary Domains
313(15)
9.3.1 Document Understanding
313(2)
9.3.2 Image Understanding
315(3)
9.3.3 Biometrics
318(5)
9.3.4 Security Printing
323(5)
9.4 Secondary Domains
328(12)
9.4.1 Surveillance
328(6)
9.4.2 Optical Character Recognition
334(3)
9.4.3 Security Analytics
337(3)
9.5 Summary
340(2)
References
341(1)
10 Building More Robust Systems
342(18)
10.1 Introduction
342(1)
10.2 Summarization
342(8)
10.2.1 Ground Truthing for Meta-algorithmics
342(5)
10.2.2 Meta-algorithmics for Keyword Generation
347(3)
10.3 Cloud Systems
350(3)
10.4 Mobile Systems
353(2)
10.5 Scheduling
355(1)
10.6 Classification
356(2)
10.7 Summary
358(2)
Reference
359(1)
11 The Future
360(9)
11.1 Recapitulation
360(2)
11.2 The Pattern of All Patience
362(3)
11.3 Beyond the Pale
365(2)
11.4 Coming Soon
367(1)
11.5 Summary
368(1)
References
368(1)
Index 369
Steven J. Simske, Hewlett-Packard Labs, Colorado, USA Dr Simske is currently Director of the Document Ecosystem Lab, at Hewlett-Packard Labs, Colorado, USA. He has been working in algorithms, imaging, machine learning and classification for the past 20 years. As an engineer at HP Labs, he has designed, developed and shipped products associated with a very broad array of domainsdocument understanding, image segmentation and understanding, speech recognition, medical signal processing and imaging, biometrics, natural language processing, surveillance, optical character recognition, security analytics and security printing. The advantages of systematic meta-algorithmic approaches to the robustness, accuracy, cost and/or other system features which is the focus of the book has been evident across these domains. Dr. Simske is an HP Fellow, IS&T Fellow and IEEE Senior Member. He has published 300 articles and book chapters; and holds 45 US Patents primarily in the areas of classification, machine learning, and large system design and development.
Biežāk uzdotie jautājumi par e-grāmatām Biežāk uzdotie jautājumi par e-grāmatām
Permanent link: https://www.kriso.lv/db/97811186267022e.html
Keywords: