logo资料库

Building.Intelligent.Systems.A.Guide.to.Machine.Learning.Engineering..pdf

发布时间：2022-06-19 发布人：admin 分类：说明书 资料大小：3.39M 资料格式：pdf 举报 版权申诉
第1页 / 共346页
第2页 / 共346页
第3页 / 共346页
第4页 / 共346页
第5页 / 共346页
第6页 / 共346页
第7页 / 共346页
第8页 / 共346页
资料共346页，剩余部分请下载后查看
    Table of Contents
    About the Author
    About the Technical Reviewer
    Acknowledgments
    Introduction
    Part I: Approaching an Intelligent Systems Project
    Chapter 1: Introducing Intelligent Systems
    Elements of an Intelligent System
    An Example Intelligent System
    The Internet Toaster
    Using Data to Toast
    Sensors and Heuristic Intelligence
    Toasting with Machine Learning
    Making an Intelligent System
    Summary
    For Thought…
    Chapter 2: Knowing When to Use Intelligent Systems
    Types of Problems That Need Intelligent Systems
    Big Problems
    Open-Ended Problems
    Time-Changing Problems
    Intrinsically Hard Problems
    Situations When Intelligent Systems Work
    When a Partial System Is Viable and Interesting
    When You Can Use Data from the System to Improve
    When the System Can Interface with the Objective
    When it is Cost Effective
    When You Aren’t Sure You Need an Intelligent System
    Summary
    For Thought
    Chapter 3: A Brief Refresher on Working with Data
    Structured Data
    Asking Simple Questions of Data
    Working with Data Models
    Conceptual Machine Learning
    Common Pitfalls of Working with Data
    Summary
    For Thought
    Chapter 4: Defining the Intelligent System’s Goals
    Criteria for a Good Goal
    An Example of Why Choosing Goals Is Hard
    Types of Goals
    Organizational Objectives
    Leading Indicators
    User Outcomes
    Model Properties
    Layering Goals
    Ways to Measure Goals
    Waiting for More Information
    A/B Testing
    Hand Labeling
    Asking Users
    Decoupling Goals
    Keeping Goals Healthy
    Summary
    For Thought
    Part II: Intelligent Experiences
    Chapter 5: The Components of Intelligent Experiences
    Presenting Intelligence to Users
    An Example of Presenting Intelligence
    Achieve the System’s Objectives
    An Example of Achieving Objectives
    Minimize Intelligence Flaws
    Create Data to Grow the System
    An Example of Collecting Data
    Summary
    For Thought…
    Chapter 6: Why Creating Intelligent Experiences Is Hard
    Intelligence Make Mistakes
    Intelligence Makes Crazy Mistakes
    Intelligence Makes Different Types of Mistakes
    Intelligence Changes
    The Human Factor
    Summary
    For Thought…
    Chapter 7: Balancing Intelligent Experiences
    Forcefulness
    Frequency
    Value of Success
    Cost of Mistakes
    Knowing There Is a Mistake
    Recovering from a Mistake
    Intelligence Quality
    Summary
    For Thought…
    Chapter 8: Modes of Intelligent Interaction
    Automate
    Prompt
    Organize
    Annotate
    Hybrid Experiences
    Summary
    For Thought…
    Chapter 9: Getting Data from Experience
    An Example: TeamMaker
    Simple Interactions
    Making It Fun
    Connecting to Outcomes
    Properties of Good Data
    Context, Actions, and Outcomes
    Good Coverage
    Real Usage
    Unbiased
    Does Not Contain Feedback Loops
    Scale
    Ways to Understand Outcomes
    Implicit Outcomes
    Ratings
    Reports
    Escalations
    User Classifications
    Summary
    For Thought…
    Chapter 10: Verifying Intelligent Experiences
    Getting Intended Experiences
    Working with Context
    Working with Intelligence
    Bringing it Together
    Achieving Goals
    Continual Verification
    Summary
    For Thought…
    Part III: Implementing Intelligence
    Chapter 11: The Components of an Intelligence Implementation
    An Example of Intelligence Implementation
    Components of an Intelligence Implementation
    The Intelligence Runtime
    Intelligence Management
    Intelligence Telemetry Pipeline
    The Intelligence Creation Environment
    Intelligence Orchestration
    Summary
    For Thought…
    Chapter 12: The Intelligence Runtime
    Context
    Feature Extraction
    Models
    Execution
    Results
    Instability in Intelligence
    Intelligence APIs
    Summary
    For Thought…
    Chapter 13: Where Intelligence Lives
    Considerations for Positioning Intelligence
    Latency in Updating
    Quality Is Evolving Quickly
    Problem Changing Quickly
    Risk of Costly Mistakes
    Latency in Execution
    Latency in Intelligent Experience
    The Right Answer Changes Drastically
    Cost of Operation
    The Cost of Distributing Intelligence
    The Cost of Executing Intelligence
    Offline Operation
    Places to Put Intelligence
    Static Intelligence in the Product
    Client-Side Intelligence
    Server-Centric Intelligence
    Back-End (Cached) Intelligence
    Hybrid Intelligence
    Summary
    For Thought…
    Chapter 14: Intelligence Management
    Overview of Intelligence Management
    Complexity in Intelligent Management
    Frequency in Intelligence Management
    Human Systems
    Sanity-Checking Intelligence
    Checking for Compatibility
    Checking for Runtime Constraints
    Checking for Obvious Mistakes
    Lighting Up Intelligence
    Single Deployment
    Silent Intelligence
    Controlled Rollout
    Flighting
    Turning Off Intelligence
    Summary
    For Thought…
    Chapter 15: Intelligent Telemetry
    Why Telemetry Is Needed
    Make Sure Things Are Working
    Understand Outcomes
    Gather Data to Grow Intelligence
    Properties of an Effective Telemetry System
    Sampling
    Summarizing
    Flexible Targeting
    Common Challenges
    Bias
    Rare Events
    Indirect Value
    Privacy
    Summary
    For Thought…
    Part IV: Creating Intelligence
    Chapter 16: Overview of Intelligence
    An Example Intelligence
    Contexts
    Implemented at Runtime
    Available for Intelligence Creation
    Things Intelligence Can Predict
    Classifications
    Probability Estimates
    Regressions
    Rankings
    Hybrids and Combinations
    Summary
    For Thought…
    Chapter 17: Representing Intelligence
    Criteria for Representing Intelligence
    Representing Intelligence with Code
    Representing Intelligence with Lookup Tables
    Representing Intelligence with Models
    Linear Models
    Decision Trees
    Neural Networks
    Summary
    For Thought…
    Chapter 18: The Intelligence Creation Process
    An Example of Intelligence Creation: Blinker
    Understanding the Environment
    Define Success
    Get Data
    Bootstrap Data
    Data from Usage
    Get Ready to Evaluate
    Simple Heuristics
    Machine Learning
    Understanding the Tradeoffs
    Assess and Iterate
    Maturity in Intelligence Creation
    Being Excellent at Intelligence Creation
    Data Debugging
    Verification-Based Approach
    Intuition with the Toolbox
    Math (?)
    Summary
    For Thought…
    Chapter 19: Evaluating Intelligence
    Evaluating Accuracy
    Generalization
    Types of Mistakes
    Distribution of Mistakes
    Evaluating Other Types of Predictions
    Evaluating Regressions
    Evaluating Probabilities
    Evaluating Rankings
    Using Data for Evaluation
    Independent Evaluation Data
    Independence in Practice
    Evaluating for Sub-Populations
    The Right Amount of Data
    Comparing Intelligences
    Operating Points
    Curves
    Subjective Evaluations
    Exploring the Mistakes
    Imagining the User Experience
    Finding the Worst Thing
    Summary
    For Thought…
    Chapter 20: Machine Learning Intelligence
    How Machine Learning Works
    The Pros and Cons of Complexity
    Underfitting
    Overfitting
    Balancing Complexity
    Feature Engineering
    Converting Data to Useable Format
    Helping your Model Use the Data
    Normalizing
    Exposing Hidden Information
    Expanding the Context
    Eliminating Misleading Things
    Modeling
    Complexity Parameters
    Identifying Overfitting
    Summary
    For Thought…
    Chapter 21: Organizing Intelligence
    Reasons to Organize Intelligence
    Properties of a Well-Organized Intelligence
    Ways to Organize Intelligence
    Decouple Feature Engineering
    Multiple Model Searches
    Chase Mistakes
    Meta-Models
    Model Sequencing
    Partition Contexts
    Overrides
    Summary
    For Thought…
    Part V: Orchestrating Intelligent Systems
    Chapter 22: Overview of Intelligence Orchestration
    Properties of a Well-Orchestrated Intelligence
    Why Orchestration Is Needed
    Objective Changes
    Users Change
    Problem Changes
    Intelligence Changes
    Costs Change
    Abuse
    The Orchestration Team
    Summary
    For Thought…
    Chapter 23: The Intelligence Orchestration Environment
    Monitor the Success Criteria
    Inspect Interactions
    Balance the Experience
    Override Intelligence
    Create Intelligence
    Summary
    For Thought…
    Chapter 24: Dealing with Mistakes
    The Worst Thing That Could Happen
    Ways Intelligence Can Break
    System Outage
    Model Outage
    Intelligence Errors
    Intelligence Degradation
    Mitigating Mistakes
    Invest in Intelligence
    Balance the Experience
    Adjust Intelligence Management Parameters
    Implement Guardrails
    Override Errors
    Summary
    For Thought…
    Chapter 25: Adversaries and Abuse
    Abuse Is a Business
    Abuse Scales
    Estimating Your Risk
    What an Abuse Problem Looks Like
    Ways to Combat Abuse
    Add Costs
    Becoming Less Interesting to Abusers
    Machine Learning with an Adversary
    Get the Abuser out of the Loop
    Summary
    For Thought…
    Chapter 26: Approaching Your Own Intelligent System
    An Intelligent System Checklist
    Approach the Intelligent System Project
    Plan for the Intelligent Experience
    Plan the Intelligent System Implementation
    Get Ready to Create Intelligence
    Orchestrate Your Intelligent System
    Summary
    For Thought…
    Index
    分享到：
    赞 收藏

    相关推荐

    资料库

    人工智能

    共收录2047份资料，累计62个分类，关注成员有19位，主要包括：GNSS,Pico-SIM868-GSM,GPRS,NB-IoT,GPRSHAT,SIM7070GCat-M,GNSSHAT,GSM,NB-IoTHAT,SIM7080GCat-M,R800CGSM,SIM800CGSM,UPSPowerModule(B),UPSPowerModule,Pico-SIM7020C-NB-IoT,SIM7028NB-IoTHAT,SIM7020CNB-IoTHAT,SIM7000XNB-IoTHAT,A7670CCat-1HAT,A7600C1Cat-1,SIM7600X4G&LTECat-1HAT,SIM7600X4GDONGLE用户手册,RM520N-GL5GHAT,RM500Q-GL5GHAT,RM500U-CN5GHAT,SIM820X-M25GforJetsonNano,AudioCardforJetsonNano,SIM7600G-H4GforJetsonNano,OpenNCC-Lite-4G8M,IMX219-77Camera,13.3inche-PaperHAT,10.3inche-PaperHAT(D),10.3inche-PaperHAT,9.7inche-PaperHAT,7.8inche-PaperHAT,6inchHDTouche-PaperHAT,6inchHDe-PaperHAT,6inche-PaperHAT,5.83inche-PaperHAT(C),LCD-Clock-A,0.95inchRGBOLED(A),0.96inchRGBOLEDModule,0.96inchOLEDModule,0.96inchOLED(A),1.27inchRGBOLEDModule,1.3inchOLEDModule(C),1.3inchOLED(A),1.32inchOLEDModule,1.5inchRGBOLEDModule,1.5inchOLEDModule,JETSONORINNX,自然语言处理,搜索引擎,VR,计算广告,深度学习,机器学习

    热门标签

    GNSS Pico-SIM868-GSM GPRS NB-IoT GPRSHAT SIM7070GCat-M GNSSHAT GSM NB-IoTHAT SIM7080GCat-M R800CGSM SIM800CGSM UPSPowerModule(B) UPSPowerModule Pico-SIM7020C-NB-IoT SIM7028NB-IoTHAT SIM7020CNB-IoTHAT SIM7000XNB-IoTHAT A7670CCat-1HAT A7600C1Cat-1 SIM7600X4G&LTECat-1HAT SIM7600X4GDONGLE用户手册 RM520N-GL5GHAT RM500Q-GL5GHAT RM500U-CN5GHAT SIM820X-M25GforJetsonNano AudioCardforJetsonNano SIM7600G-H4GforJetsonNano OpenNCC-Lite-4G8M IMX219-77Camera 13.3inche-PaperHAT 10.3inche-PaperHAT(D) 10.3inche-PaperHAT 9.7inche-PaperHAT 7.8inche-PaperHAT 6inchHDTouche-PaperHAT 6inchHDe-PaperHAT 6inche-PaperHAT 5.83inche-PaperHAT(C) LCD-Clock-A 0.95inchRGBOLED(A) 0.96inchRGBOLEDModule 0.96inchOLEDModule 0.96inchOLED(A) 1.27inchRGBOLEDModule 1.3inchOLEDModule(C) 1.3inchOLED(A) 1.32inchOLEDModule 1.5inchRGBOLEDModule 1.5inchOLEDModule JETSONORINNX 自然语言处理 搜索引擎 VR 计算广告 深度学习 机器学习

    最新资料