The Mythos of Model Interpretability
|
|
- Ross Ellis
- 5 years ago
- Views:
Transcription
1 The Mythos of Model Interpretability Zachary C. Lipton
2 Outline What is interpretability? What are its desiderata? What model properties confer interpretability? Caveats, pitfalls, and takeaways
3 What is Interpretability? Many papers make axiomatic claims that some model is interpretable and therefore preferable But what interpretability is and precisely what desiderata it serves are seldom defined Does interpretability hold consistent meaning across papers?
4 Inconsistent Definitions Papers use the words interpretable, explainable, intelligible, transparent, and understandable, both interchangeably (within papers) and inconsistently (across papers) One common thread, however, is that interpretability is something other than performance
5 We want good models Evaluation Metric
6 We also want interpretable models Evaluation Metric Interpretation
7 The Human Wants Something the Metric Doesn t Evaluation Metric Interpretation
8 What Gives? So either the metric captures everything and people seeking interpretable models are crazy or The metric / loss functions we optimize are fundamentally mismatched from real life objectives We hope to refine the discourse on interpretability, introducing more specific language Through the lens of the literature, we create a taxonomy of both objectives & methods
9 Outline What is interpretability? What are its desiderata? What model properties confer interpretability? Caveats, pitfalls, and takeaways
10 Trust Does the model know when it s uncertain? Does the model make same mistakes as human? Are we comfortable with the model?
11 Causality We may want models to tell us something about the natural world Supervised models are trained simply to make predictions, but often used to take actions Caruana (2015) shows a mortality predictor (for use in triage) that assigns lower risk to asthma patients
12 Transferability The idealized training setups often differ from real world Real problem may be non-stationary, noisier, etc. Want sanity-checks that the model doesn t depend on weaknesses in setup
13 Informativeness We may train a model to make a decision But it s real purpose is to aid a person in making a decision Thus an interpretation may simply be valuable for the extra bits it carries
14 Outline What is interpretability? What are its desiderata? What model properties confer interpretability? Caveats, pitfalls, and takeaways
15 Transparency Proposed solutions conferring interpretability tend to fall into two categories Transparency addresses understanding how the model works Explainability concerns the model s ability to offer some (potentially post-hoc) explanation
16 Simulatability One notion of transparency is simplicity This accords with papers advocating small decision trees A model is transparent if a person can step through the algorithm in reasonable time
17 Decomposability A relaxed notion requires understanding individual components of a model Such as: weights of a linear model or the nodes of a decision tree
18 Transparent Algorithms A yet weaker notion would require only that we understand the behavior algorithm E.g. convergence of convex optimizations, generalization bounds
19 Post-Hoc Interpretability Ah yes, something cool is happening in node 750,345,167 maybe it sees a cat? Maybe we ll see something awesome if we jiggle the inputs?
20 Verbal Explanations Just as people generate explanations (absent transparency), we might train a (possibly separate) model to generate explanations We might consider image captions as interpretations of object predictions (Image: Karpathy et al 2015)
21 Saliency Maps While the full relationship between input and output might be impossible to describe succinctly, local explanations are potentially useful. (Image: Wang et al 2016)
22 Case-Based Explanations Another way to generate a post-hoc explanation might be to retrieve labeled items that are deemed similar by the model For some models, we can retrieve histories from similar patients (Image: Mikolov et al 2014)
23 Outline What is interpretability? What are its desiderata? What model properties confer interpretability? Caveats, pitfalls, and takeaways
24 Discussion Points Linear models not strictly more interpretable than deep learning Claims about interpretability must be qualified Transparency may be at odds with the goals of AI Post-hoc interpretations may potentially mislead
25 Thanks! Acknowledgments: Zachary C. Lipton was supported by the Division of Biomedical Informatics at UCSD, via training grant (T15LM011271) from the NIH/NLM. Thanks to Charles Elkan, Julian McAuley, David Kale, Maggie Makar, Been Kim, Lihong Li, Rich Caruana, Daniel Fried, Jack Berkowitz, & Sepp Hochreiter References: The Mythos of Model Interpretability (ICML Workshop on Human Interpretability 2016) - ZC Lipton Directly Modeling Missing Data with RNNs (MLHC 2016) - ZC Lipton, DC Kale, R Wetzel Learning to Diagnose (ICLR 2016) - ZC Lipton, DC Kale, Charles Elkan, R Wetzel Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. (2015) - R Caruana et al
The Mythos of Model Interpretability
Zachary C. Lipton University of California, San Diego 9500 Gilman Drive, La Jolla, CA 92093 USA ZLIPTON@CS.UCSD.EDU Abstract Supervised machine learning models boast remarkable predictive capabilities.
More informationApplied Machine Learning, Lecture 11: Ethical and legal considerations; domain effects and domain adaptation
Applied Machine Learning, Lecture 11: Ethical and legal considerations; domain effects and domain adaptation Richard Johansson including some slides borrowed from Barbara Plank overview introduction bias
More informationIntroduction to Machine Learning. Katherine Heller Deep Learning Summer School 2018
Introduction to Machine Learning Katherine Heller Deep Learning Summer School 2018 Outline Kinds of machine learning Linear regression Regularization Bayesian methods Logistic Regression Why we do this
More informationArtificial Intelligence to Enhance Radiology Image Interpretation
Artificial Intelligence to Enhance Radiology Image Interpretation Curtis P. Langlotz, MD, PhD Professor of Radiology and Biomedical Informatics Associate Chair, Information Systems, Department of Radiology
More informationThe Mythos of Model Interpretability
Zachary C. Lipton 1 Often, our machine learning problem formulations are imarxiv:1606.03490v3 [cs.lg] 6 Mar 2017 Abstract Supervised machine learning models boast remarkable predictive capabilities. But
More informationPolitical Science 15, Winter 2014 Final Review
Political Science 15, Winter 2014 Final Review The major topics covered in class are listed below. You should also take a look at the readings listed on the class website. Studying Politics Scientifically
More informationMotivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience.
Outline: Motivation. What s the attention mechanism? Soft attention vs. Hard attention. Attention in Machine translation. Attention in Image captioning. State-of-the-art. 1 Motivation: Attention: Focusing
More informationWhy did the network make this prediction?
Why did the network make this prediction? Ankur Taly (Google Inc.) Joint work with Mukund Sundararajan and Qiqi Yan Some Deep Learning Successes Source: https://www.cbsinsights.com Deep Neural Networks
More informationA Guide to Reading a Clinical or Research Publication
A Guide to Reading a Clinical or Research Publication For people living with a rare disease, being able to read and understand the information found in a clinical or research publication can be especially
More informationAssurance Activities Ensuring Triumph, Avoiding Tragedy Tony Boswell
Assurance Activities Ensuring Triumph, Avoiding Tragedy Tony Boswell CLEF Technical Manager SiVenture 1 Overview What are Assurance Activities? How do they relate to earlier CC work? What are we looking
More informationENGAGING THE CONSUMER VOICE
ENGAGING THE CONSUMER VOICE Katherine Cavanaugh, Consumer Advocate, National HCH Council Danielle Orlando, Peer Advocate, Project HOPE This activity is made possible by grant number U30CS09746 from the
More informationData and Statistics 101: Key Concepts in the Collection, Analysis, and Application of Child Welfare Data
TECHNICAL REPORT Data and Statistics 101: Key Concepts in the Collection, Analysis, and Application of Child Welfare Data CONTENTS Executive Summary...1 Introduction...2 Overview of Data Analysis Concepts...2
More informationArtificial Intelligence: Its Scope and Limits, by James Fetzer, Kluver Academic Publishers, Dordrecht, Boston, London. Artificial Intelligence (AI)
Artificial Intelligence: Its Scope and Limits, by James Fetzer, Kluver Academic Publishers, Dordrecht, Boston, London. Artificial Intelligence (AI) is the study of how to make machines behave intelligently,
More informationExperimental Research in HCI. Alma Leora Culén University of Oslo, Department of Informatics, Design
Experimental Research in HCI Alma Leora Culén University of Oslo, Department of Informatics, Design almira@ifi.uio.no INF2260/4060 1 Oslo, 15/09/16 Review Method Methodology Research methods are simply
More informationAugust 29, Introduction and Overview
August 29, 2018 Introduction and Overview Why are we here? Haavelmo(1944): to become master of the happenings of real life. Theoretical models are necessary tools in our attempts to understand and explain
More informationMachine Learning for Healthcare: What next? David Sontag Clinical Machine Learning Group MIT
Machine Learning for Healthcare: What next? David Sontag Clinical Machine Learning Group MIT Readings References for risk stratification Population-Level Prediction of Type 2 Diabetes using Claims Data
More information2019 Judging Form Through the Lens of Culture Mental Health Matters Category
2019 Judging Form Through the Lens of Culture Mental Health Matters Category Dear Judge, We encourage you to seek personal support if you become troubled by the content of this category. If you experience
More informationDirect access to intelligent care for healthier muscles, joints and bones. Working Body Member guide
Direct access to intelligent care for healthier muscles, joints and bones Working Body Member guide October 2015 Helping you keep your muscles, joints and bones healthy Chances are you don t give your
More informationGenomics Research. May 31, Malvika Pillai
Genomics Research May 31, 2018 Malvika Pillai Outline for Research Discussion Why Informatics Read journal articles! Example Paper Presentation Research Pipeline How To Read A Paper If I m aiming to just
More informationDEEP LEARNING BASED VISION-TO-LANGUAGE APPLICATIONS: CAPTIONING OF PHOTO STREAMS, VIDEOS, AND ONLINE POSTS
SEOUL Oct.7, 2016 DEEP LEARNING BASED VISION-TO-LANGUAGE APPLICATIONS: CAPTIONING OF PHOTO STREAMS, VIDEOS, AND ONLINE POSTS Gunhee Kim Computer Science and Engineering Seoul National University October
More informationSAMPLE. Conners 3 Self-Report Assessment Report. By C. Keith Conners, Ph.D.
By C. Keith Conners, Ph.D. Conners 3 Self-Report Assessment Report This Assessment report is intended for use by qualified assessors only, and is not to be shown or presented to the respondent or any other
More informationPsychology Perception
Psychology 343 - Perception James R. Sawusch, 360 Park Hall jsawusch@buffalo.edu 645-0238 TA is Timothy Pruitt, 312 Park tapruitt@buffalo.edu Text is Sensation & Perception by Goldstein (8th edition) PSY
More informationTesting the robustness of anonymization techniques: acceptable versus unacceptable inferences - Draft Version
Testing the robustness of anonymization techniques: acceptable versus unacceptable inferences - Draft Version Gergely Acs, Claude Castelluccia, Daniel Le étayer 1 Introduction Anonymization is a critical
More informationHow Does Analysis of Competing Hypotheses (ACH) Improve Intelligence Analysis?
How Does Analysis of Competing Hypotheses (ACH) Improve Intelligence Analysis? Richards J. Heuer, Jr. Version 1.2, October 16, 2005 This document is from a collection of works by Richards J. Heuer, Jr.
More informationYou can use this app to build a causal Bayesian network and experiment with inferences. We hope you ll find it interesting and helpful.
icausalbayes USER MANUAL INTRODUCTION You can use this app to build a causal Bayesian network and experiment with inferences. We hope you ll find it interesting and helpful. We expect most of our users
More informationHow do Categories Work?
Presentations Logistics Think about what you want to do Thursday we ll informally sign up, see if we can reach consensus. Topics Linear representations of classes Non-linear representations of classes
More informationInterview Guide Related to PCP and Patient Characteristics
RSNA, 2016 10.1148/radiol.2016152188 Appendix E1 Interview Guide Related to PCP and Patient Characteristics My name is and I am a research coordinator at XXX. Thank you again for agreeing to participate
More informationThe Standard Theory of Conscious Perception
The Standard Theory of Conscious Perception C. D. Jennings Department of Philosophy Boston University Pacific APA 2012 Outline 1 Introduction Motivation Background 2 Setting up the Problem Working Definitions
More informationDeep Diabetologist: Learning to Prescribe Hypoglycemia Medications with Hierarchical Recurrent Neural Networks
Deep Diabetologist: Learning to Prescribe Hypoglycemia Medications with Hierarchical Recurrent Neural Networks Jing Mei a, Shiwan Zhao a, Feng Jin a, Eryu Xia a, Haifeng Liu a, Xiang Li a a IBM Research
More informationThinking Ahead. Advance Care Planning for People with Developmental Disabilities
Thinking Ahead Advance Care Planning for People with Developmental Disabilities Objectives Review principles and importance of ACP Describe the steps of the ACP process Describe the role of patient, proxy,
More informationPolicy Gradients. CS : Deep Reinforcement Learning Sergey Levine
Policy Gradients CS 294-112: Deep Reinforcement Learning Sergey Levine Class Notes 1. Homework 1 milestone due today (11:59 pm)! Don t be late! 2. Remember to start forming final project groups Today s
More informationAutonomous Mobile Robotics
1 2 3 A reflex arc is a neural pathway that controls a reflex. In vertebrates, most sensory neurons do not pass directly into the brain, but synapse in the spinal cord. This allows for faster reflex actions
More informationYou can use this app to build a causal Bayesian network and experiment with inferences. We hope you ll find it interesting and helpful.
icausalbayes USER MANUAL INTRODUCTION You can use this app to build a causal Bayesian network and experiment with inferences. We hope you ll find it interesting and helpful. We expect most of our users
More informationFactors for Measuring Dramatic Believability. Brian Magerko, Ph.D. Games for Entertainment and Learning Lab Michigan State University
Factors for Measuring Dramatic Believability Brian Magerko, Ph.D. Games for Entertainment and Learning Lab Michigan State University Outline Introduction Deconstruction Evaluation from Player Perspective
More informationEvolutionary Programming
Evolutionary Programming Searching Problem Spaces William Power April 24, 2016 1 Evolutionary Programming Can we solve problems by mi:micing the evolutionary process? Evolutionary programming is a methodology
More informationSupplementary notes for lecture 8: Computational modeling of cognitive development
Supplementary notes for lecture 8: Computational modeling of cognitive development Slide 1 Why computational modeling is important for studying cognitive development. Let s think about how to study the
More informationIt has often been said that there is no greater crime than the waste CATALYTIC CONVERTER
The creation of a thinking environment allows client and coach to find solutions together. But how can the coach be a catalyst for the client s own ideas without putting words into their mouths? By Nancy
More information1. Improve Documentation Now
Joseph C. Nichols, MD, Principal, Health Data Consulting, Seattle, Washington From Medscape Education Family Medicine: Transition to ICD-10: Getting Started. Posted: 06/19/2012 Target Audience: This activity
More informationLogic Model. When do you create a Logic Model? Create your LM at the beginning of an evaluation and review and update it periodically.
RRC Evaluation Tool Basket: Logic Model 1 Logic Model What is a Logic Model? A logic model is a series of if-then statements that outlines what you expect to happen in your program. For example, If these
More informationCognitive illusions in development and testing
1 Edinburgh, Cognitive illusions in development and testing Prepared and presented by Grove Consultants Dorothy Graham Mark Fewster Lloyd Roden Clive Bates Grove House 40 Ryles Park Road Macclesfield SK11
More informationFOSTERING TRAUMA-INFORMED LEADERSHIP SKILLS FOR CONSUMERS
FOSTERING TRAUMA-INFORMED LEADERSHIP SKILLS FOR CONSUMERS This project was supported by the Health Resources and Services Administration (HRSA) of the U.S. Department of Health and Human Services (HHS)
More informationPSYC 441 Cognitive Psychology II
PSYC 441 Cognitive Psychology II Session 4 Background of Object Recognition Lecturer: Dr. Benjamin Amponsah, Dept., of Psychology, UG, Legon Contact Information: bamponsah@ug.edu.gh College of Education
More informationRecognizing Ambiguity
Recognizing Ambiguity How Lack of Information Scares Us Mark Clements Columbia University I. Abstract In this paper, I will examine two different approaches to an experimental decision problem posed by
More informationDeep Learning Models for Time Series Data Analysis with Applications to Health Care
Deep Learning Models for Time Series Data Analysis with Applications to Health Care Yan Liu Computer Science Department University of Southern California Email: yanliu@usc.edu Yan Liu (USC) Deep Health
More informationLean Body Mass and Muscle Mass What's the Difference?
Lean Body Mass and Muscle Mass What's the Difference? PUBLISHED ON SEPTEMBER 24, 2015 BY RYAN WALTERS Consider the following three statements: I m not trying to get huge; I just want to put on five pounds
More informationOUTLINE OF PRESENTATION
Swimming Race Day Execution Sean McCann Ph.D. USOC Senior Sport Psychologist Sean McCann Ph.D., USOC sean.mccann@usoc.org OUTLINE OF PRESENTATION 2 Introductions Three Skill Sets for performing under pressure
More informationPractical Bayesian Optimization of Machine Learning Algorithms. Jasper Snoek, Ryan Adams, Hugo LaRochelle NIPS 2012
Practical Bayesian Optimization of Machine Learning Algorithms Jasper Snoek, Ryan Adams, Hugo LaRochelle NIPS 2012 ... (Gaussian Processes) are inadequate for doing speech and vision. I still think they're
More informationChapter 12 Conclusions and Outlook
Chapter 12 Conclusions and Outlook In this book research in clinical text mining from the early days in 1970 up to now (2017) has been compiled. This book provided information on paper based patient record
More informationRoss Jeffries Speed Seduction
Ross Jeffries Speed Seduction How To Meet Women Anytime, Anywhere (10-Part Seduction Mastery Series) Part 2: Avoid the Confidence Trap www.seduction.com This transcript may not be duplicated without written
More informationA Comment on the Absent-Minded Driver Paradox*
Ž. GAMES AND ECONOMIC BEHAVIOR 20, 25 30 1997 ARTICLE NO. GA970508 A Comment on the Absent-Minded Driver Paradox* Itzhak Gilboa MEDS KGSM, Northwestern Uni ersity, E anston, Illinois 60201 Piccione and
More informationStages of Recovery Interview Schedule
Stages of Recovery Interview Schedule Recovery from mental illness can be described as the growth of hope, a positive sense of self, meaning and purpose in life, and being in control of one s life. It
More informationDavid Chalmers, The hard problem of consciousness
24.09x Minds and Machines David Chalmers, The hard problem of consciousness Excerpts from David Chalmers, The hard problem of consciousness, in The Norton Introduction to Philosophy, edited by Gideon Rosen,
More informationAssessing the Foundations of Conscious Computing: A Bayesian Exercise
Assessing the Foundations of Conscious Computing: A Bayesian Exercise Eric Horvitz June 2001 Questions have long been posed with about whether we might one day be able to create systems that experience
More informationHow to Help Your Patients Overcome Anxiety with Mindfulness
How to Help Your Patients Overcome Anxiety with Mindfulness Bonus 1 - Transcript - pg. 1 How to Help Your Patients Overcome Anxiety with Mindfulness How to Find the Limits of Fear and Anxiety with Ron
More informationHealthcare Research You
DL for Healthcare Goals Healthcare Research You What are high impact problems in healthcare that deep learning can solve? What does research in AI applications to medical imaging look like? How can you
More informationMBT and adherence to model. Sigmund Karterud
MBT and adherence to model Sigmund Karterud Treatment integrity Does the therapist actually do/deliver what the treatment is supposed to consist of? I.e.: Is the therapist «on model»? How do we measure
More informationSMALL n IMPACT EVALUATION. Howard White and Daniel Phillips 3ie
SMALL n IMPACT EVALUATION Howard White and Daniel Phillips 3ie MY PRIORS Bad evaluation Good evaluation MY PRIORS MY PRIORS MY PRIORS All projectaffected persons (PAPs) DEFINITIONS I Impact evaluations
More informationNew Mexico TEAM Professional Development Module: Autism
[Slide 1]: Welcome Welcome to the New Mexico TEAM technical assistance module on making eligibility determinations under the category of autism. This module will review the guidance of the NM TEAM section
More informationNeuromorphic convolutional recurrent neural network for road safety or safety near the road
Neuromorphic convolutional recurrent neural network for road safety or safety near the road WOO-SUP HAN 1, IL SONG HAN 2 1 ODIGA, London, U.K. 2 Korea Advanced Institute of Science and Technology, Daejeon,
More informationNew Mexico TEAM Professional Development Module: Deaf-blindness
[Slide 1] Welcome Welcome to the New Mexico TEAM technical assistance module on making eligibility determinations under the category of deaf-blindness. This module will review the guidance of the NM TEAM
More informationCRITICAL APPRAISAL OF QUALITATIVE STUDIES
CRITICAL APPRAISAL OF QUALITATIVE STUDIES Rationale for research: Does the paper describe an important clinical problem and is the question clearly formulated? If yes, continue with the form below. If
More informationOur previous accounts of perceptual experience accepted the phenomenal principle:
PHL340 Handout 3: Representationalism 1 Representationalism and the Phenomenal Principle An experience s representational content is the way the world must be if the experience is to be veridical. Representationalism
More informationCAREER BASE CAMP Day 2: Leverage Your Emotional Intelligence
CAREER BASE CAMP Day 2: Leverage Your Emotional Intelligence for Career Success REBECCA MCDONALD SENIOR CAREER COACH CURRENT M.A. COUNSELING CANDIDATE Notes Every year I work closely with recruiters and
More informationThe Logic of Data Analysis Using Statistical Techniques M. E. Swisher, 2016
The Logic of Data Analysis Using Statistical Techniques M. E. Swisher, 2016 This course does not cover how to perform statistical tests on SPSS or any other computer program. There are several courses
More informationYour goal in studying for the GED science test is scientific
Science Smart 449 Important Science Concepts Your goal in studying for the GED science test is scientific literacy. That is, you should be familiar with broad science concepts and how science works. You
More informationMultiple Regression Models
Multiple Regression Models Advantages of multiple regression Parts of a multiple regression model & interpretation Raw score vs. Standardized models Differences between r, b biv, b mult & β mult Steps
More informationThe Thesis Writing Process and Literature Review
The Thesis Writing Process and Literature Review From Splattered Ink Notes to Refined Arguments Christy Ley Senior Thesis Tutorial October 10, 2013 Overview: Thesis Structure! Introduction! Literature
More information04/12/2014. Research Methods in Psychology. Chapter 6: Independent Groups Designs. What is your ideas? Testing
Research Methods in Psychology Chapter 6: Independent Groups Designs 1 Why Psychologists Conduct Experiments? What is your ideas? 2 Why Psychologists Conduct Experiments? Testing Hypotheses derived from
More informationA SITUATED APPROACH TO ANALOGY IN DESIGNING
A SITUATED APPROACH TO ANALOGY IN DESIGNING JOHN S. GERO AND JAROSLAW M. KULINSKI Key Centre of Design Computing and Cognition Department of Architectural & Design Science University of Sydney, NSW 2006,
More informationDiscovery ENGINEERS ASK THE BRAIN TO SAY, "CHEESE!"
1 of 5 5/22/2014 9:36 AM Discovery ENGINEERS ASK THE BRAIN TO SAY, "CHEESE!" How do we take an accurate picture of the world s most complex biological structure? A new imaging techniqu lets researchers
More informationBehaviorism: An essential survival tool for practitioners in autism
Behaviorism: An essential survival tool for practitioners in autism What we re going to do today 1. Review the role of radical behaviorism (RB) James M. Johnston, Ph.D., BCBA-D National Autism Conference
More informationOn the diversity principle and local falsifiability
On the diversity principle and local falsifiability Uriel Feige October 22, 2012 1 Introduction This manuscript concerns the methodology of evaluating one particular aspect of TCS (theoretical computer
More informationDeveloping A Health Pro Mindset
Developing A Health Pro Mindset By: Katie Tietz, MS, OTR/L Contact Information Katie@healthpromindset.com www.healthpromindset.com Participants completing this workshop will be able to: 1. Describe the
More informationUCSD EXPERIENCE, DESIGNING AND IMPLEMENTING CORRECTIVE ACTIONS. Derek Brown
UCSD EXPERIENCE, DESIGNING AND IMPLEMENTING CORRECTIVE ACTIONS Derek Brown 2 Design and implementation of corrective actions Outline 1. Designing corrective actions Something has gone wrong, what are you
More informationImage Captioning using Reinforcement Learning. Presentation by: Samarth Gupta
Image Captioning using Reinforcement Learning Presentation by: Samarth Gupta 1 Introduction Summary Supervised Models Image captioning as RL problem Actor Critic Architecture Policy Gradient architecture
More informationTalking with parents about vaccines for children
Talking with parents about vaccines for children Strategies for health care professionals THIS RESOURCE COVERS: - What you may hear from parents about their vaccine safety questions and how to effectively
More informationProcessing of Logical Functions in the Human Brain
Processing of Logical Functions in the Human Brain GRMELA ALEŠ AGCES Ltd. AGCES, Levského 3221/1, Praha 4 CZECH REPUBLIC N. E. MASTORAKIS Military Institutions of University Education, Hellenic Naval Academy,
More informationChapter 11 Nonexperimental Quantitative Research Steps in Nonexperimental Research
Chapter 11 Nonexperimental Quantitative Research (Reminder: Don t forget to utilize the concept maps and study questions as you study this and the other chapters.) Nonexperimental research is needed because
More informationOVERVIEW TUTORIAL BEHAVIORAL METHODS CLAIM: EMLAR VII EYE TRACKING: READING. Lecture (50 min) Short break (10 min) Computer Assignments (30 min)
EMLAR VII EYE TRACKING: READING Arnout Koornneef a.w.koornneef@uu.nl OVERVIEW TUTORIAL Lecture (50 min) Basic facts about reading Examples Advantages and disadvantages of eye tracking Short break (10 min)
More informationUNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014
UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014 Exam policy: This exam allows two one-page, two-sided cheat sheets (i.e. 4 sides); No other materials. Time: 2 hours. Be sure to write
More informationThe Truth About Fitness, Weight Loss and Improving Athletic Performance by Kevin Quinlan
The Truth About Fitness, Weight Loss and Improving Athletic Performance by Kevin Quinlan First of all, let me set your mind at ease I m NOT trying to sell you anything here! The purpose of this report
More informationAuthors face many challenges when summarising results in reviews.
Describing results Authors face many challenges when summarising results in reviews. This document aims to help authors to develop clear, consistent messages about the effects of interventions in reviews,
More informationStudy Endpoint Considerations: Final PRO Guidance and Beyond
Study Endpoint Considerations: Final PRO Guidance and Beyond Laurie Burke Associate Director for Study Endpoints and Labeling OND/CDER/FDA Presented at: FIRST ANNUAL PATIENT REPORTED OUTCOMES (PRO) CONSORTIUM
More informationFinding Information Sources by Model Sharing in Open Multi-Agent Systems 1
Finding Information Sources by Model Sharing in Open Multi-Agent Systems Jisun Park, K. Suzanne Barber The Laboratory for Intelligent Processes and Systems The University of Texas at Austin 20 E. 24 th
More informationTeacher In-Service: Interpreters in the Classroom
Teacher In-Service: Interpreters in the Classroom Dear Parents, At the start of a new school year, teachers and staff may be unfamiliar with interpreters in the classroom. In some cases, there is no access
More informationDraft National Adult Immunization Plan
2015 National Adult Immunization and Influenza Summit National Adult Immunization Plan Ilka Chavez Chief of Operations and Management National Vaccine Program Office U.S. Department of Health and Human
More informationCSE 258 Lecture 2. Web Mining and Recommender Systems. Supervised learning Regression
CSE 258 Lecture 2 Web Mining and Recommender Systems Supervised learning Regression Supervised versus unsupervised learning Learning approaches attempt to model data in order to solve a problem Unsupervised
More informationAn Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns
An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns 1. Introduction Vasily Morzhakov, Alexey Redozubov morzhakovva@gmail.com, galdrd@gmail.com Abstract Cortical
More informationSAMPLE. Conners 3 Self-Report Assessment Report. By C. Keith Conners, Ph.D.
By C. Keith Conners, Ph.D. Conners 3 Self-Report Assessment Report This Assessment report is intended for use by qualified assessors only, and is not to be shown or presented to the respondent or any other
More informationAfter Rescorla-Wagner
After Rescorla-Wagner W. Jeffrey Wilson March 6, 2013 RW Problems STM-LTM & Learning SOP Model Configural vs Elemental Nodes Problems with Rescorla-Wagner Model Extinction: No Spontaneous Recovery or Rapid
More informationArtificial intelligence (and Searle s objection) COS 116: 4/29/2008 Sanjeev Arora
Artificial intelligence (and Searle s objection) COS 116: 4/29/2008 Sanjeev Arora Artificial Intelligence Definition of AI (Merriam-Webster): The capability of a machine to imitate intelligent human behavior
More informationPolicy Gradients. CS : Deep Reinforcement Learning Sergey Levine
Policy Gradients CS 294-112: Deep Reinforcement Learning Sergey Levine Class Notes 1. Homework 1 due today (11:59 pm)! Don t be late! 2. Remember to start forming final project groups Today s Lecture 1.
More informationCourse summary, final remarks
Course "Empirical Evaluation in Informatics" Prof. Dr. Lutz Prechelt Freie Universität Berlin, Institut für Informatik http://www.inf.fu-berlin.de/inst/ag-se/ Role of empiricism Generic method Concrete
More informationarxiv: v2 [cs.ai] 26 Sep 2018
Manipulating and Measuring Model Interpretability arxiv:1802.07810v2 [cs.ai] 26 Sep 2018 Forough Poursabzi-Sangdeh forough.poursabzi@microsoft.com Microsoft Research Jennifer Wortman Vaughan jenn@microsoft.com
More informationACADEMIC APPLICATION:
Academic Skills: Critical Thinking Bloom s Taxonomy Name Point of the Assignment: To help you realize there are different forms of critical thinking to be used in education. Some forms of critical thinking
More informationWinter - Recover Your Health Cleanse Your Colon
Winter - Recover Your Health Cleanse Your Colon Answers to Frequently Asked Questions There has been lots of interest in the Nourishing Food Winter Cleanse. I am hoping these answers allow you to know
More informationInternal Requirements for Change Agents
for Change Agents The True Purpose Process The inner game of becoming a powerful change agent is of paramount importance. In its ordinary configuration, the ego is not properly tuned and optimized to be
More informationEcholalia Worksheet. 1. Please describe an example of echolalia. 2. Please circle the option that best describes your examples.
Echolalia Worksheet 1. Please describe an example of echolalia. 2. Please circle the option that best describes your examples. Immediate Delayed Both 3. Use the ABC model to describe the events that typically
More information