Visualizations For Justifying Machine Learning Predictions David - PowerPoint PPT Presentation

Mar 17, 2024 •25 likes •145 views

Visualizations For Justifying Machine Learning Predictions David Johnson 1 Motivation Strengths of ML allowed expansion to diverse fields Fields and contexts far removed from traditional ML Users not trained in ML Eg. Medical

Visualizations For Justifying Machine Learning Predictions David Johnson 1
Motivation • Strengths of ML allowed expansion to diverse fields • Fields and contexts far removed from traditional ML • Users not trained in ML • Eg. Medical field: Doctors use ML to predict disease given symptoms • The ML is a black box to them: Input → ? → Output 2
Previous Work Figure: Biran, O., MckKeown, K. (2014). Justification Narratives for Individual Classifications. AutoML workshop at ICML 2014 . 3
Previous Work Some issues: ● The vis relies on NLG quite a bit ● Vis isn’t very clear for non-experts (what is Y-Prior? What is Slope?) Figure: Biran, O., MckKeown, K. (2014). Justification Narratives for Individual Classifications. AutoML workshop at ICML 2014 . 4
Goals • Justify a ML prediction to a non-expert user • Show features providing evidence for/against the prediction • Select and visualize key features • Focus on interpretable models • Simplicity not complexity... 5 Figure: Munzner, T. (2014). Visualization Analysis and Design. CRC Press.
Goals • Justify a ML prediction to a non-expert user • Show features providing evidence for/against the prediction • Select and visualize key features • Focus on interpretable models • Simplicity not complexity... 6 Figure: Munzner, T. (2014). Visualization Analysis and Design. CRC Press.
Feature Visualizing Vis can show effect and importance 1 • Effect: extent to which a feature contributes toward or against prediction • Importance: Expected effect of the feature for a particular class (mean feature value for the class) 1 Biran, O., MckKeown, K. (2014). Justification Narratives for Individual Classifications. AutoML workshop at ICML 2014 . 7
Abstraction • Some raw data: arbitrary data with training/test sets • Task abstraction: - Analyze: discover, enjoy, derive • Data abstraction: - Items, attributes, values in a table • Two quantitative variables: effect, importance -- scatterplot effective 8
Demo 9
Future Direction NLG implemented Full web app implementation Expanded scope: 10
Thanks! Questions? 11
12

Recommend

On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study

On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection Vivian Lai and Chenhao Tan @vivwylai | @chenhaotan vivlai.github.io | chenhaot.com University of Colorado Boulder

391 views • 24 slides

Overview CS 446 What is machine learning? Machine learning : study of computational

Overview CS 446 What is machine learning? Machine learning : study of computational mechanisms that learn from data to make predictions and decisions. 1 / 21 Application 1: image classification Birdwatcher takes photos of birds,

1.08k views • 83 slides

Introduction to machine learning COMS 4721 Learning from data Machine learning : the study

Introduction to machine learning COMS 4721 Learning from data Machine learning : the study of computational mechanisms that learn from data in order to make predictions and decisions. Example 1: image classification A birdwatcher

932 views • 14 slides

Hedging Predictions in Machine Learning Alex Gammerman and Zhiyuan Luo zhiyuan@cs.rhul.ac.uk

Hedging Predictions in Machine Learning Alex Gammerman and Zhiyuan Luo zhiyuan@cs.rhul.ac.uk Computer Learning Research Centre Dept of Computer Science Royal Holloway, University of London Egham, Surrey TW20 0EX, UK Networks and Data Mining

1.35k views • 113 slides

Bike share traffic predictions using machine learning Arnab Kumar Datta Agenda

Bike share traffic predictions using machine learning Arnab Kumar Datta Agenda Introduction to bike-sharing Motivation and vision A short introduction to machine learning Overview of software Results Conclusion

572 views • 46 slides

A Hands-On Introduction to Automatic Machine Learning Lars Kotthofg University of Wyoming

A Hands-On Introduction to Automatic Machine Learning Lars Kotthofg University of Wyoming larsko@uwyo.edu AutoML Workshop, 28 August 2018, Nanjing 1 Machine Learning Data Machine Learning Predictions 2 Automatic Machine Learning

744 views • 33 slides

Machine-Learning Methods in Property Predictions: Quo Vadis ? Igor I. Baskin Lomonosov Moscow

Machine-Learning Methods in Property Predictions: Quo Vadis ? Igor I. Baskin Lomonosov Moscow State University RUSSIA 1 General Workflow for QSAR Modiling in Chemoinformatics A Structure Descriptors T Model r N

758 views • 31 slides

Euro 2016 Predictions Using Team Rating Systems Jan Lasek deepsense.io Machine Learning and

Euro 2016 Predictions Using Team Rating Systems Jan Lasek deepsense.io Machine Learning and Data Mining for Sports Analytics Workshop at ECML PKDD 2016 Jan Lasek (deepsense.io) Euro 2016 Predictions MLSA at ECML PKDD16 1 / 14

575 views • 23 slides

Week 6 Video 5 Visualization Other Awesome EDM Visualizations Other Awesome EDM Visualizations

Week 6 Video 5 Visualization Other Awesome EDM Visualizations Other Awesome EDM Visualizations Not an exhaustive list For obvious reasons Learnograms A graph that shows the change in one learning- related variable over time Concept

411 views • 11 slides

INFO 1998: Introduction to Machine Learning Lecture 3: Data Visualization INFO 1998: Introduction

INFO 1998: Introduction to Machine Learning Lecture 3: Data Visualization INFO 1998: Introduction to Machine Learning Agenda 1. Why Data Visualization is Important 2. Data Visualization Libraries 3. Basic Visualizations 4. Advanced Visualizations

546 views • 28 slides

Justifying the State Protection and Power Review: Justifying the state: What are the ultimate

Justifying the State Protection and Power Review: Justifying the state: What are the ultimate goals? How can our loss of freedom can be justified! OK here are some justifications Consent: The social contract Power is its own

916 views • 36 slides

Multiple Instance Learning for Fast, Stable and Early RNN Predictions Don Dennis , Microsoft

The Edge of Machine Learning Multiple Instance Learning for Fast, Stable and Early RNN Predictions Don Dennis , Microsoft Research India, Joint work with Chirag P., Harsha and Prateek Accepted to NIPS 18 1 Algorithms for the IDE - EdgeML

977 views • 70 slides

Machine Learning and Data Mining Nearest neighbor methods Kalev Kask Supervised learning

+ Machine Learning and Data Mining Nearest neighbor methods Kalev Kask Supervised learning Notation Features x Targets y Predictions Parameters q Learning algorithm Change q Program (Learner) Improve performance

366 views • 21 slides

Machine Learning and Data Mining Linear regression Kalev Kask Supervised learning Notation

+ Machine Learning and Data Mining Linear regression Kalev Kask Supervised learning Notation Features x Targets y Predictions Parameters q Learning algorithm Change q Program (Learner) Improve performance

1.28k views • 71 slides

An Exercise in An Exercise in Machine Learning Machine Learning

An Exercise in An Exercise in Machine Learning Machine Learning http://www.cs.iastate.edu/~cs573x/bbsilab.html Machine Learning Software Preparing Data Building Classifiers Interpreting Results Machine Learning Software

496 views • 26 slides

Machine Learning in PandaRoot GlueX-Panda Workshop G.Washington University, May 2019 Ralf Kliemt

Machine Learning in PandaRoot GlueX-Panda Workshop G.Washington University, May 2019 Ralf Kliemt (GSI) Motivation Machine Learning (ML) is about modelling data Self-learning algorithms gain knowledge from data to make predictions Why?

626 views • 39 slides

Machine Learning By Alex Scarlatos What is Machine Learning? Machine Learning is the process by

Machine Learning By Alex Scarlatos What is Machine Learning? Machine Learning is the process by which computers can be trained through observation, rather than being explicitly programmed. Basically, a program is given input and adjusts its

556 views • 17 slides

Machine Learning: Study of algorithms that improve their performance P at some task T

Machine Learning 10-601 Tom M. Mitchell Machine Learning Department Carnegie Mellon University January 12, 2015 Today: Readings: What is machine learning? The Discipline of ML Decision tree learning Mitchell, Chapter 3

872 views • 29 slides

Traditional Machine Learning: Unsupervised Learning Juhan Nam Traditional Machine Learning

GCT634/AI613: Musical Applications of Machine Learning (Fall 2020) Traditional Machine Learning: Unsupervised Learning Juhan Nam Traditional Machine Learning Pipeline in Classification Tasks A set of hand-designed audio features are selected

398 views • 26 slides

Plotting & Visualization Maryam Tavakol Machine Learning Group Winter semester 2016/17 1

Plotting & Visualization Maryam Tavakol Machine Learning Group Winter semester 2016/17 1 Motivation Making plots and static or interactive visualizations is one of the most important tasks in data analysis Helping identify outliers

673 views • 28 slides

CS 335 Machine Learning What is Machine Learning? Dan Sheldon Spring 2019 What is Machine

1/22/19 CS 335 Machine Learning What is Machine Learning? Dan Sheldon Spring 2019 What is Machine Learning? A Simple Task: Recognize Obama How do you program a computer to Recognize faces? Recommend movies? Decide which web

581 views • 5 slides

Machine Learning Machine Learning: algorithms that use experience to improve their

Machine Learning Machine Learning: algorithms that use experience to improve their performance We use machine learning in situations where it is very challenging (or impossible) to define the rules by hand: e.g. face detection

1.04k views • 28 slides

Learning and Meta-learning computation making predictions choosing actions

Learning and Meta-learning computation making predictions choosing actions acquiring episodes statistics algorithm gradient ascent ( eg of the likelihood) correlation Kalman filtering implementation

1.05k views • 56 slides

Introduction to Machine Learning COMPSCI 371D Machine Learning COMPSCI 371D Machine

Introduction to Machine Learning COMPSCI 371D Machine Learning COMPSCI 371D Machine Learning Introduction to Machine Learning 1 / 12 Outline 1 Nearest Neighbor Prediction 2 Complexity Considerations 3 The Voronoi Diagram 4 Overfitting

564 views • 12 slides