The “Assembly Line” for the Information Age Human-Computer Cooperation for Large-Scale Product Classification Jianfu Chen Computer Science Department,

Slides:



Advertisements
Similar presentations
BEHAVIORAL RESEARCH IN MANAGERIAL ACCOUNTING RANJANI KRISHNAN HARVARD BUSINESS SCHOOL & MICHIGAN STATE UNIVERSITY 2008.
Advertisements

Autonomic Scaling of Cloud Computing Resources
Manufacturing and Service Technologies
© 2006 MVTec Software GmbH Press Colloquium Part II Building Technology for the Customer’s Advantage.
Presentation Topic : Modeling Human Vaccinating Behaviors On a Disease Diffusion Network PhD Student : Shang XIA Supervisor : Prof. Jiming LIU Department.
Leadership & Technology
9- Copyright 2007 Prentice Hall 1 Organizational Theory, Design, and Change Fifth Edition Gareth R. Jones Chapter 9 Organizational Design, Competences,
1-1 Operations Management Introduction - Chapter 1.
Chapter 1 Introduction to Operations Management. Three Functions in a Business Marketing – to “sell” products Operations – to “make” products Finance.
McGraw-Hill/Irwin ©2005 The McGraw-Hill Companies, All rights reserved ©2005 The McGraw-Hill Companies, All rights reserved McGraw-Hill/Irwin.
Chapter 2. History of Performance Improvement Daniel B. McLaughlin Julie M. Hays Healthcare Operations Management.
Smart Home Technologies CSE 4392 / CSE 5392 Spring 2006 Manfred Huber
The Academy of Public administration under the President of the Republic of Uzbekistan APPLICATION MODERN INFORMATION AND COMMUNICATION TECHNOLOGY IN DECISION.
ALBERT PARK EEL 6788: ADVANCED TOPICS IN COMPUTER NETWORKS Energy-Accuracy Trade-off for Continuous Mobile Device Location, In Proc. of the 8th International.
History of Industrial Engineering (IE)
Semantic Web Technologies Lecture # 2 Faculty of Computer Science, IBA.
Choosing a Research Topic Patrice Koehl Computer Science, UC Davis.
The Implementing Function & Motivation and Change Management Erin Napier Taylor Buckles Connor Strange C.
Data Mining Chun-Hung Chou
L5: The Gilded Age: Working Conditions The Shifting Size and Scope of the National Government: Part One Agenda Objective: 1.To understand what working.
Week 6 Lecture Normalization
Crowdsourcing Predictors of Behavioral Outcomes. Abstract Generating models from large data sets—and deter¬mining which subsets of data to mine—is becoming.
Chapter 6 Motivation.
Human-Centered Information Visualization Jiajie Zhang, Kathy Johnson, Jack Smith University of Texas at Houston Jane Malin NASA Johnson Space Center July.
The Evolution of Management Theory
Matching IT to People & Organizations
Introduction to Advertising
11 C H A P T E R Artificial Intelligence and Expert Systems.
{ Logic in Artificial Intelligence By Jeremy Wright Mathematical Logic April 10 th, 2012.
The New Manager. Learning Objectives Understand the relationship between management and the organization Appreciate the evolution of management thought.
1 Chapter 1 Introduction to Advertising. 2 What Makes an Ad Great? Explicit objectives should drive the planning, creation, and execution of each ad.
COSC 3461: Module 1 S04 Introduction to Interaction & Principles of Design I.
Trust-Aware Optimal Crowdsourcing With Budget Constraint Xiangyang Liu 1, He He 2, and John S. Baras 1 1 Institute for Systems Research and Department.
Crowdsourcing with Multi- Dimensional Trust Xiangyang Liu 1, He He 2, and John S. Baras 1 1 Institute for Systems Research and Department of Electrical.
3DCS Advanced Analyzer/Optimizer Module © Dimensional Control Systems Inc DCS Advanced Analyzer/Optimizer Equation Based Tolerance Analysis Quick.
Industrial Revolution
Technology The practical use of human knowledge to extend human abilities and to satisfy human needs and wan ts.
1. 2 Traditional Income Statement LO1: Prepare a contribution margin income statement.
21 - Adulthood: Cognitive Development. What is intelligence? Spearman’s “G” ◦ General intelligence ◦ One basic trait ◦ Inferred from vocabulary, memory,
A Context Model based on Ontological Languages: a Proposal for Information Visualization School of Informatics Castilla-La Mancha University Ramón Hervás.
Fundamentals of Information Systems, Sixth Edition1 Natural Language Processing and Voice Recognition Processing that allows the computer to understand.
Strategic Planning and Goal Setting
Learning from Model-Produced Graphs in a Climate Change Science Class Catherine Gautier Geography Department UC Santa Barbara.
Fundamentals of Information Systems, Third Edition1 The Knowledge Base Stores all relevant information, data, rules, cases, and relationships used by the.
Management Fundamentals - Schermerhorn & Wright
Unsupervised Mining of Statistical Temporal Structures in Video Liu ze yuan May 15,2011.
1 Increase Value Reduce Waste/Cost Strategic warehouse management direction in the next 18 months Rex Ma, Senior consultant, SCM PRODCUT SOLUTIONS, Oracle.
6.01 PowerPoint 6.01 Understand skills required for seeking employment.
Information Technology
Artificial Intelligence: Research and Collaborative Possibilities a presentation by: Dr. Ernest L. McDuffie, Assistant Professor Department of Computer.
Using Bayesian Networks to Predict Plankton Production from Satellite Data By: Rob Curtis, Richard Fenn, Damon Oberholster Supervisors: Anet Potgieter,
Adulthood: Cognitive Development Age 25 + What is adult IQ, and how does expertise develop?
Predicting Consensus Ranking in Crowdsourced Setting Xi Chen Mentors: Paul Bennett and Eric Horvitz Collaborator: Kevyn Collins-Thompson Machine Learning.
Saving Bitrate vs. Users: Where is the Break-Even Point in Mobile Video Quality? ACM MM’11 Presenter: Piggy Date:
1 MGT8200 Organizing to Compete What is an organization?
Information and Information Technology 1. Information and employment 2.
An Introduction to Cost Terms and Purposes © 2009 Pearson Prentice Hall. All rights reserved.
Brief Intro to Machine Learning CS539
7.2 Scarcity & Opportunity Cost
Manufacturing and Service Technologies
Chapter 2: Management Theorists
Chapter Outline Scientific Management Theory
Designing Organizational Structure
CSCI 5822 Probabilistic Models of Human and Machine Learning
Basic Intro Tutorial on Machine Learning and Data Mining
Organizational Design, Competences, and Technology
Frederick W. Taylor How Did Taylor’s Approach to Management
Flow of Probabilistic Influence
Kostas Kolomvatsos, Christos Anagnostopoulos
Goals for Learning in the Geosciences
Presentation transcript:

The “Assembly Line” for the Information Age Human-Computer Cooperation for Large-Scale Product Classification Jianfu Chen Computer Science Department, Stony Brook University

Machines Transform Human History

People have always been seeking the optimal way of integrating machine and human labor.

20 th Century Ford Assembly Line Integrates Machine and Human Labor Efficiently

21 st Century – Information Age “Mass Production” of Information

We want to find the optimal ways to integrate machine and human intelligence. NOT all products could be produced fully automatically by machines – assembly line integrated machine & human labor NOT all information can be produced fully automatically by computers – We want to find optimal ways to integrate machine and human intelligence What’s the “Assembly Line” for the Information Age?

A Case Study: Large scale product classification Kindle Fire HD 8.9" 4G LTE Wireless 8.9" HD Display, Dolby Audio, Dual- Band Dual-Antenna Wi-Fi, 4G LTE, 32GB or 64GB Goal: optimally integrate computer and human effort Achieve a lower unit cost for product classification More precisely, optimize the accuracy-cost tradeoff

An “Assembly Line” for Human Computer Cooperation 3Com V.35 cable V.35 cable ( DTE ) - DB-50 (M) - M/34 (V.35) (M) - 10 ft A list of K candidate classes System Accuracy Machine Accuracy Human Accuracy X Cost is Human labor cost, i.e., the salary paid to workers, which is proportional to the working time spent. =

A quick glance at Accuracy-Cost Relation

There is an optimal cost that gives the highest accuracy.

Towards a more realistic analysis of accuracy-cost relationship With the above “assembly line” model, human accuracy and working time are influenced by a set of factors – K – Task difficulty – Expertise I am familiar with office supplies, but not familiar with nuts and bolts. – Cognitive characteristics Careful, smart, quick Independent of the task

Use a probabilistic graphical model to capture the cognitive process of human classification A probabilistic graphical model shows how the above different factors interact with each other, and influence the accuracy and cost. Specifically, we use Bayesian Network, which characterizes the causal relationships of different factors.

Use a Bayesian Network to predict accuracy and cost

Not only visually intuitive, but also formal

Inference and learning

usage of the model Predict the accuracy-cost tradeoff – Given certain budget, what’s the highest accuracy we can achieve? – To achieve certain accuracy, what’s the lowest expected cost? How to charge customers? Optimally assign the workers to the tasks

Related Works time and motion study – Scientific management (Taylorism) Crowdsourcing – Amazon Mechanical Turk – learning worker expertise and accuracy Item Response Theory – Psychometrics IQ test, GRE, GMAT

Conclusion In information age, we need a new “assembly line” to integrate human and machine intelligence. We try to model human accuracy and working time by considering the interactions of a set of relevant factors, using a probabilistic graphical model. We use the model to predict the accuracy-cost tradeoff, decide how to charge customers, and optimally assign tasks to human workers.

Thank you!