Muutke küpsiste eelistusi

E-raamat: Reverse Hypothesis Machine Learning: A Practitioner's Perspective

4.50/5 (4 hinnangut Goodreads-ist)
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 135,23 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Reverse Hypothesis Machine Learning: A Practitioner's PerspectiveSuurem pilt
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

This book introduces a paradigm of reverse hypothesis machines (RHM), focusing on knowledge innovation and machine learning. Knowledge- acquisition -based learning is constrained by large volumes of data and is time consuming. Hence Knowledge innovation based learning is the need of time. Since under-learning results in cognitive inabilities and over-learning compromises freedom, there is need for optimal machine learning. All existing learning techniques rely on mapping input and output and establishing mathematical relationships between them. Though methods change the paradigm remains the same—the forward hypothesis machine paradigm, which tries to minimize uncertainty. The RHM, on the other hand, makes use of uncertainty for creative learning. The approach uses limited data to help identify new and surprising solutions. It focuses on improving learnability, unlike traditional approaches, which focus on accuracy. The book is useful as a reference book for machine learning researchers and professionals as well as machine intelligence enthusiasts. It can also used by practitioners to develop new machine learning applications to solve problems that require creativity.

Part I Building Foundation: Decoding Knowledge Acquisition
1 Introduction: Patterns Apart
3(20)
1.1 A Naked World of Data Warriors!
4(2)
1.2 Introduction---The Blind Data Game
6(1)
1.3 Putting Creativity on Weak Legs: Can We Make Present Machines Creative?
7(1)
1.4 Learning Using Creative Models
8(1)
1.5 Plundered Every Data Point---Data Rich Knowledge Poor Society
8(1)
1.6 Computational Creativity and Data Analysis
9(2)
1.7 Simple Paradigms and Evaluations: (Machine Learning Compass and Barometer)
11(1)
1.8 After All Its Time for Knowledge Innovation---Do not just Build Innovate
11(1)
1.9 What Is Knowledge Innovation? (Meta-Knowledge Approach)
12(2)
1.10 Knowledge Innovation Model Building
14(2)
1.11 Creative Intelligence to Collective Knowledge Innovation: (Intelligible Togetherness)
16(1)
1.12 Do not Dive Deep Unnecessarily: (Your Machine Learning Life Guard in Deep Data Sea)
17(1)
1.13 Machine Learning and Knowledge Innovation
17(1)
1.14 Making Intelligent Agent Intelligent
18(3)
1.15 Architecting Intelligence
21(1)
1.16 Summary
22(1)
2 Understanding Machine Learning Opportunities
23(26)
2.1 Understanding Learning Opportunity (Catching Data Signals Right)
27(3)
2.2 Knowledge Innovation Building Blocks of ML and Intelligent Systems
30(1)
2.3 Stages in Limited Exploration
30(2)
2.4 Mathematical Equations for Classification
32(7)
2.5 New Paradigms in This Book
39(1)
2.6 iknowlation's IDEA Matrix for Machine Learning Opportunity Evaluation
40(3)
2.7 Using IDEA Matrix to Identify ML Opportunity
43(2)
2.8 Self-evaluation of Learning
45(1)
2.9 Mathematical Model of Learnability
45(1)
2.10 Building Machine Learning Models: Your Foundation for Surprising Solutions
46(1)
2.11 Opportunity Cycle
46(1)
2.12 ML Big Landscape
47(1)
2.13 Context-Based Learning---Respect Heterogeneity
47(1)
2.14 Summary
48(1)
3 Systemic Machine Learning
49(10)
3.1 What Is a System? (Decoding Connectivity)
51(3)
3.2 What Is Systemic Machine Learning: (Exploiting Togetherness)
54(1)
3.3 Systemic Machine Learning Model and Algorithm Selection
55(1)
3.4 Cognitive Systemic Machine Learning Models
55(1)
3.5 Cognitive Interaction Centric Models
56(1)
3.6 Meta-Reasoning Centric Models (System of System)
56(2)
3.6.1 System Study
58(1)
3.6.2 Learning with Limited Data
58(1)
3.7 Summary
58(1)
4 Reinforcement and Deep Reinforcement Machine Learning
59(28)
4.1 Introduction
59(1)
4.2 Reinforcement Learning
60(8)
4.3 Learning Agents
68(3)
4.4 Returns and Reward Calculations (Evaluate Your Position and Actions)
71(2)
4.5 Dynamic Systems (Making Best Use of Unpredictability)
73(1)
4.6 Dynamic Environment and Dynamic System
74(1)
4.7 Reinforcement Learning and Exploration
74(1)
4.8 Markov Property and Markov Decision Process
75(1)
4.9 Value Functions
75(1)
4.10 Action and Value
76(1)
4.11 Learning an Optimal Policy (Model-Based and Model-Free Methods)
77(1)
4.12 Uncertainty
77(1)
4.13 Adaptive Dynamic Learning (Learning Evolution)
77(1)
4.14 Temporal Difference (TD) Learning
78(1)
4.15 Q Learning
79(1)
4.16 Unified View
80(1)
4.17 Deep Exploratory Machine Learning
81(2)
4.18 Summary
83(4)
Part II Learnability Route: Reverse Hypothesis Machines
5 Creative Machine Learning
87(32)
5.1 Forward Hypothesis Learning
88(1)
5.2 Behavior-Driven Learning to Hypothesis-Driven Learning
89(1)
5.3 Mathematical Formulation of Hypothesis-Based Learning
90(1)
5.4 Data Mapping with Forward Hypothesis Machine
91(1)
5.5 How It Works
92(1)
5.6 Data Acquisition Machines
93(1)
5.7 Knowledge Acquisition Machines
94(1)
5.8 Forward Hypothesis Machines Basic Structure
94(2)
5.9 Exploratory Forward Hypothesis Machines
96(1)
5.10 New Learnability Measures
96(5)
5.11 Reverse Hypothesis Learning: (Beginning with Improbable)
101(2)
5.12 Getting Creativity in Action Through Reverse Hypothesis
103(4)
5.13 Methods for Reverse Hypothesis Learning
107(1)
5.14 Collaborative Hypothesis Learning
107(2)
5.15 Why Reverse Hypothesis Machines Are Different
109(3)
5.16 Reverse Hypothesis Machine and Metasearch
112(1)
5.17 Machine with Man
112(1)
5.18 A Process for Creative Systemic Machine Learning (CSML)
112(3)
5.19 Identification and Verification of Context Neighbor
115(1)
5.20 Context Vector Machine
115(1)
5.21 Example of Context Determination
116(1)
5.22 Summary
117(2)
6 Co-operative and Collective Learning for Creative ML
119(6)
6.1 Crowd Powered System
119(1)
6.2 Types of Crowdsourcing
120(1)
6.3 Intelligent Collective Learning---Taking Crowdsourcing to Next Level
121(1)
6.4 ML in Action---Intelligently Handling Crowdsourced Data
121(1)
6.5 Collective Intelligence
121(2)
6.6 Collaborative Filtering
123(1)
6.7 Learning Map Begins
124(1)
6.8 The Maps Combine to Collaboration
124(1)
6.9 Summary
124(1)
7 Building Creative Machines with Optimal ML and Creative Machine Learning Applications
125(8)
7.1 Creativity and Architecture
126(1)
7.2 Cognitive Distance
126(2)
7.3 Exploring Conceptual Spaces and Going Beyond
128(2)
7.4 Expanding Conceptual Boundaries
130(1)
7.5 Meta-Reasoning (Thinking About Thinking)
131(1)
7.6 Summary
132(1)
8 Conclusion---Learning Continues
133(2)
Bibliography 135(2)
Index 137
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97833195531226e.html
Märksõnad: