RESOLVER: To ask or to sense? A brief presentation of the ongoing project by Nikolaos Mavridis.

Slides:



Advertisements
Similar presentations
SCIENCE PROCESS SKILLS
Advertisements

Chapter 2 The Process of Experimentation
Curriculum Development and Course Design
Animal, Plant & Soil Science
Computer-Based Performance Assessments from NAEP and ETS and their relationship to the NGSS Aaron Rogat Educational Testing Service.
3. Basic Topics in Game Theory. Strategic Behavior in Business and Econ Outline 3.1 What is a Game ? The elements of a Game The Rules of the.
Week 11 Review: Statistical Model A statistical model for some data is a set of distributions, one of which corresponds to the true unknown distribution.
Stages in Second Language Acquisition
Consistency of Assessment
From requirements to design
VALIDITY.
Report on Intrusion Detection and Data Fusion By Ganesh Godavari.
Statistics for Managers Using Microsoft Excel, 4e © 2004 Prentice-Hall, Inc. Chap 7-1 Chapter 7 Confidence Interval Estimation Statistics for Managers.
Evaluating Hypotheses
05/06/2005CSIS © M. Gibbons On Evaluating Open Biometric Identification Systems Spring 2005 Michael Gibbons School of Computer Science & Information Systems.
The SLO Process Session 2 updated October 28, 2014 Denver Public Schools Assessment, Research and Evaluation, 2014.
Chapter One of Your Thesis
Statistical Natural Language Processing. What is NLP?  Natural Language Processing (NLP), or Computational Linguistics, is concerned with theoretical.
Discussion 1: Theory.
Introduction to Theory & Research Design
Statistics for Managers Using Microsoft Excel, 4e © 2004 Prentice-Hall, Inc. Chap 7-1 Chapter 7 Confidence Interval Estimation Statistics for Managers.
Framework for K-12 Science Education
THE PRINCIPLE OF ALIGNMENT EDA 122. ALIGNMENT OUTCOMES PROCESS.
Second World Congress on Positive Psychology (July 23-26, 2011; Philadelphia, Pennsylvania, USA) Choice as self-orientation activity in real life situations.
Dr. Engr. Sami ur Rahman Assistant Professor Department of Computer Science University of Malakand Research Methods in Computer Science Lecture: Research.
14. Introduction to inference
Studying Visual Attention with the Visual Search Paradigm Marc Pomplun Department of Computer Science University of Massachusetts at Boston
What research is Noun: The systematic investigation into and study of materials and sources in order to establish facts and reach new conclusions. Verb:
Knowing what you get for what you pay An introduction to cost effectiveness FETP India.
Curriculum development A brief guide to the construction of relevant curricula.
Volunteer?. What’s the population of Raleigh? How many people live in Raleigh?
Big Idea 1: The Practice of Science Description A: Scientific inquiry is a multifaceted activity; the processes of science include the formulation of scientifically.
NEURAL NETWORKS FOR DATA MINING
Report on Intrusion Detection and Data Fusion By Ganesh Godavari.
Educational Psychology, 7 th edition Jeanne E. Ormrod © 2011 Pearson Education, Inc. All rights reserved. 1-1 Understanding research.
Inquiry-based Learning Linking Teaching with Learning.
Quantitative and Qualitative Approaches
Datasets on the GRID David Adams PPDG All Hands Meeting Catalogs and Datasets session June 11, 2003 BNL.
CHAPTER 1 Understanding RESEARCH
Foundations of Physics Science Inquiry. Science Process of gathering and organizing information about the physical world.
MGT-491 QUANTITATIVE ANALYSIS AND RESEARCH FOR MANAGEMENT OSMAN BIN SAIF Session 16.
Exploiting Context Analysis for Combining Multiple Entity Resolution Systems -Ramu Bandaru Zhaoqi Chen Dmitri V.kalashnikov Sharad Mehrotra.
7 Systems Analysis and Design in a Changing World, Fifth Edition.
1 The Theoretical Framework. A theoretical framework is similar to the frame of the house. Just as the foundation supports a house, a theoretical framework.
Instructional Strategies Dr. Shama Mashhood DCPS-HPE Senior Registrar Medical Education KMDC.
Nursing research Is a systematic inquiry into a subject that uses various approach quantitative and qualitative methods) to answer questions and solve.
Cognitive Processes Chapter 8. Studying CognitionLanguage UseVisual CognitionProblem Solving and ReasoningJudgment and Decision MakingRecapping Main Points.
Introduction to Neural Networks and Example Applications in HCI Nick Gentile.
ID3 Algorithm Michael Crawford.
Section 6-3 Estimating a Population Mean: σ Known.
Mining Document Collections to Facilitate Accurate Approximate Entity Matching Presented By Harshda Vabale.
Creating Subjective and Objective Sentence Classifier from Unannotated Texts Janyce Wiebe and Ellen Riloff Department of Computer Science University of.
 Programming - the process of creating computer programs.
QUANTITATIVE TECHNIQUES
Lecture №1 Role of science in modern society. Role of science in modern society.
Paper III Qualitative research methodology.  Qualitative research is designed to reveal a specific target audience’s range of behavior and the perceptions.
Optimal Eye Movement Strategies In Visual Search.
A Brief Maximum Entropy Tutorial Presenter: Davidson Date: 2009/02/04 Original Author: Adam Berger, 1996/07/05
Formulating the Research Design
Selective Perception Policies for Guiding Sensing and Computation in Multimodal Systems Brief Presentation of ICMI ’ 03 N.Oliver & E.Horvitz paper Nikolaos.
Helpful hints for planning your Wednesday investigation.
#1 Make sense of problems and persevere in solving them How would you describe the problem in your own words? How would you describe what you are trying.
Creative Curriculum and GOLD Assessment: Early Childhood Competency Based Evaluation System By Carol Bottom.
Slide 7.1 Saunders, Lewis and Thornhill, Research Methods for Business Students, 5 th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009.
Evaluating Hypotheses. Outline Empirically evaluating the accuracy of hypotheses is fundamental to machine learning – How well does this estimate its.
CSc4730/6730 Scientific Visualization
CSc4730/6730 Scientific Visualization
Property consolidation for entity browsing
RESEARCH BASICS What is research?.
Biological Science Applications in Agriculture
Presentation transcript:

RESOLVER: To ask or to sense? A brief presentation of the ongoing project by Nikolaos Mavridis

Resolver: To ask or to sense? Resolver: Selecting and mixing questions with sensing actions towards referent resolution For machines to speak with humans, they must at times resolve ambiguities. Imagine having a conversational robot, which is able to carry out sensing actions in order to collect more data about its world; for example through active visual attention and touch. Suppose it is also able to gain new information linguistically by asking its human partner questions. Each kind of action, sensing and speech, has associated costs and expected payoffs. Resolver is a planning algorithm that treats these actions in a common framework, enabling such a robot to integrate both kinds of action into coherent behavior, taking into account their costs and expected goal-oriented information- theoretic rewards. Early motivation: ripley ’ s primitive ambiguity resolution dialogue system Similar information-theoretic / utilitarian frame of thought: –E. Horvitz (Microsoft), A. Gorin (AT&T) Wider picture: Language – action parallels (speech act theory, also motor neurons etc.) FINDING THE NEXT QUESTION!

Resolver: Overview The problem The program The algorithm Performance evaluation Potential as cognitive model Extensions Other applications: –Parallel theory refinement/experiment selection in science

The problem Imagine the following scenario: –A human user and a robot are sitting around a table, where some objects have been placed. The human user has selected one of the objects on the table, and asks the robot to give it to him. The robot has not yet attended to the objects. What should the robot ’ s next moves be? Should it attend to the color of the first object, and then to the sizes of all? Should it attempt to weigh an object? Or should it ask for further information, for example if the desired object is red? –Slight variation: the user provides an ambiguous partial description in his request. IN ESSENCE: Active matching under double uncertainty: for the desired target as well as the options available

The program: Initial state 4 Modes: Virtual world standalone (self-answering) / Virtual world text I/O / Virtual world speech I/O / Full mental-model and ripley connectivity

The program: Intermediate state After: “ The heavy one ” - “ Is it small? No ” - measuresize1-3 - “ Is it medium? ”

The program: Final state After: “ Is it medium? Yes ” – “ Is it black? No ” – “ Is it magenta? Yes ” Note cost breakdown. Costs might be given by master planner (tired, curious … )

The algorithm: Assumptions Assumption families: –The objects and the intended referent Nobj a priori known, unbiased choice –Measurements and descriptions of the objects Properties, senses->prop, words->prop (me&user), referent uniqueness up to linguistic description –State and gradation of uncertainty Contents of state (I, O, moves), initial state, full confidence in senses/answers (unchanging, unbiased by construction, cooperative user/hearing and nature/senses) –Priors on a solitary object “ Proximal ” sensory natural modes, & their linguistic reflection –Priors on the set of objects and the intended referent I belongs to O: interdepend., I unique in O: U interdepend. –Allowable actions Q1: “ Is it red? ” / Q2: ” What color is it? ” / Q3: ” Is it this one? ” A1:Measure prop of one O / A2:Measure prop of all O

The algorithm: Stages Stages: –State at each moment Encoding distributions –Effect of answers and sensory results on the state as a whole I-O and O-O interdependence –Evaluation of present state Calculating prob(I=Oi) –Choosing the next move Expected entropy reward of consistent answers Approx and computational tractability (underlying state of world and answer) –The effect of different cost settings Change ordering – choose dominance / Q1-Q2, A1-A2, Q-A –Fusion of expected information gain with associated costs Requirements for function

Performance evaluation & Potential as cognitive model Performance evaluation: –Quantitative: 2 baselines so far (random non-repetitive, consistent) Metrics: σ, μ of nmoves, and Σcost 20-25% better (parameters have effect!) normal modes help even more! –Qualitative: Subjective evaluation of robot behavior for specific cost settings Potential as cognitive model: –Tunable generative model (play with costs!) –Acquiring experimental human data fixations, saccades, words: relative position sensitive costs –Input-output equivalence vs. inner workings One step ahead Cost-reward fusion Artificial setting but general applicability (non-sit. context etc.)

Future plans: Extensions Relax assumptions: –Encoding distributions –Pruning by clustering and satisficing acceptability threshold –Unknown starting parameters (nobj etc.) –Non-cooperative user/nature –Imperfect linguistic/sensory channel (FUSE) –Other molecular action combinations –Multi-view object/shape id. sensory actions –Multi-step, non-approx (another baseline)

Other applications In essence: –Active matching under double uncertainty: for the desired target as well as the options available –Thus, to apply, just choose an interpretation of the structures involved! Parallel theory refinement / experiment selection in science –A number of groups of theoreticians are constructing theories in order to explain a phenomenon. The extension of these theories to wider domains of validity is a costly process. But so is the setting up of experiments in order to verify the applicability of their predictions to various domains. –Consider the identification of: Sensory property dimensions with application domains of the theories Questions for a property dimension with experiments in an application domain Answers with experimental results of the above questions Sensory actions with theoretical work towards extending theories to a domain And sensory data with the theoretical predictions which are the outcome of the above work –Thus: The user is now identified with nature; nature is questioned by experiments, and answers in the form of experimental results (or freely collected data in a domain). The table previously filled with objects now corresponds to a part of the platonic universe; a subset of the set of possible theories is on the table. One can either examine nature, or examine possible theories in order to reach a (hopefully somewhat permanent) temporary best match*. And thus science marches on, hopefully with resources better targeted towards more vital experiments and theoretical groups.

Resolver: To ask or to sense? Recap: –We started by wanting to expand Ripley ’ s ambiguity resolution dialogues –Created a general algorithm for active matching under uncertainty –It performs well for the original task –Interesting theoretical points have arisen –Also attractive as cognitive model –Many possible extensions … –Many alternative applications!

Resolver: Aftermath One can never underestimate the importance and joy of Finding the next question!