defining machine learning
play

Defining Machine Learning Dr. Alex Williams August 21, 2020 COSC - PowerPoint PPT Presentation

Sep 30, 2022 •159 likes •708 views

Defining Machine Learning Dr. Alex Williams August 21, 2020 COSC 425: Introduction to Machine Learning Fall 2020 (CRN: 44874) COSC 425: Intro. to Machine Learning 1 Syllabus Clarifications #1: No textbook requirement. (See Daume in Canvas.)

  1. Defining Machine Learning Dr. Alex Williams August 21, 2020 COSC 425: Introduction to Machine Learning Fall 2020 (CRN: 44874) COSC 425: Intro. to Machine Learning 1

  2. Syllabus Clarifications #1: No textbook requirement. (See Daume in Canvas.) #2: Added Office Hours link to Canvas. #3: Alternative Course Website http://web.eecs.utk.edu/~acw/teaching/cosc425/ COSC 425: Intro. to Machine Learning 2 2

  3. COSC 425: Intro. to Machine Learning 3 3

  4. Syllabus Clarifications #4: Modern Machine Learning à Python LearnPython (http://learnpython.org) • PythonTutor (http://pythontutor.com) • Programming w/ Mosh (https://www.youtube.com/…) • YouTube Video à 6-hour Intro to Python. • COSC 425: Intro. to Machine Learning 4 4

  5. Any Questions? Use Zoom’s “ Raise Hand ” feature, and I’ll un-mute you. COSC 425: Intro. to Machine Learning 5 5

  6. Today’s Agenda We will address: 1. What is “ Machine Learning ” (ML)? 2. How is ML operationalized? 3. What are the grand challenge of modern ML? COSC 425: Intro. to Machine Learning 6 6

  7. What is Machine Learning? COSC 425: Intro. to Machine Learning 7 7

  8. How would you define “machine learning”? Use Zoom’s “ Raise Hand ” feature, and I’ll un-mute you. COSC 425: Intro. to Machine Learning 8 8

  9. “At a basic level, machine learning is about predicting the future based on the past .” - Hal Daumé III COSC 425: Intro. to Machine Learning 9 9

  10. “Machine learning is the field of study that gives computers the ability to learn without being explicitly programmed .” - Arthur Samuel (1959) COSC 425: Intro. to Machine Learning 10 10

  11. “How can we build computer systems that automatically improve with experience , and what are the fundamental laws that govern all learning processes?” - Tom Mitchell (1998) COSC 425: Intro. to Machine Learning 11 11

  12. “A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P improves with experience E.” - Tom Mitchell (1998) COSC 425: Intro. to Machine Learning 12 12

  13. (Representation + Evaluation + Optimization) = Learning - Pedro Domingos (2012) COSC 425: Intro. to Machine Learning 13 13

  14. Mathematics Machine Statistics Learning Artificial Computer Intelligence Science Types of ML - Ryan Urbanowicz (2018) COSC 425: Intro. to Machine Learning 14 14

  15. - Someone, at some point in time. COSC 425: Intro. to Machine Learning 15 15

  16. So, what’s the right definition? Technically: All of them. COSC 425: Intro. to Machine Learning 16 16

  17. The overarching goal of these methods is to learn a function from prior data. Spoiler: Machine learning is (mostly) operationalized mathematics. COSC 425: Intro. to Machine Learning 17 17

  18. Terminology Input Variables Output Variables (Features) (Targets) tumor_size texture perimeter … outcome time Example / 18.02 27.6 117.5 N 31 Instance 17.99 10.38 122.8 N 61 20.29 14.34 135.1 R 27 … … … … … Dataset (i.e. with Input-Output Pairs) COSC 425: Intro. to Machine Learning 18 18

  19. Goal: Maximize performance for any x . Testing Data Both in Training and Test Data! x Training Data f Learning Algorithm Input-output Pairs f(x) y ( x i , y i ) Major Assumption: You have access to y i , (i.e. output variables). COSC 425: Intro. to Machine Learning 19 19

  20. What does “f” look like? Testing Data x f Linear regression as an example. f(x) y COSC 425: Intro. to Machine Learning 20 20

  21. Types of Machine Learning COSC 425: Intro. to Machine Learning 21 21

  22. Types of Machine Learning Supervised Unsupervised Reinforcement Learning Learning Learning COSC 425: Intro. to Machine Learning 22 22

  23. Supervised Learning: Classification Use-Case Criteria: • You have output variables, i.e. y i .. • Your OVs are discrete / categorical . isUTKEmail HeaderKeyword Word 1 Word 2 isSpam Example: Spam Filtering x1 Yes CS425 Hi Prof … No • Goal : Learn a function from x2 Yes Orientation Alex You … No categorical output. x2 No urgent Dear Sir … Yes x4 No cash hello I … Yes • e.g. {spam, not spam} x5 No help are you … Yes x6 Yes Survey Faculty this … No … COSC 425: Intro. to Machine Learning 24 24

  24. Supervised Learning: Regression Use-Case Criteria: • You have output variables, i.e. y i . • Your OVs are continuous . Example: Tesla Speed Control • Goal : Learn a function for a continuous output. • e.g. {0-100 MPH} COSC 425: Intro. to Machine Learning 25 25

  25. Criticism: Output Variables are Unknown. Input Variables Output Variables (Features) (Targets) tumor_size texture perimeter … outcome time X 18.02 27.6 117.5 N 31 17.99 10.38 122.8 N 61 20.29 14.34 135.1 R 27 … … … … … COSC 425: Intro. to Machine Learning 26 26

  26. Unsupervised Learning: Clustering Use-Case Criteria: • You have no output variables. Example: Unlabeled Data • Goal : Learn a function from input. • e.g. Organize the data! COSC 425: Intro. to Machine Learning 27 27

  27. Unsupervised Learning: Feature Selection Long-Term Goal. • Figure out which inputs matter. Feasible, but Challenging. • Data, data, and more data. +2000 Citations! https://arxiv.org/pdf/1112.6209.pdf COSC 425: Intro. to Machine Learning 28 28

  28. Criticism: “Learning from Data” isn’t Learning. COSC 425: Intro. to Machine Learning 29 29

  29. Reinforcement Learning Use-Case Criteria: • You have a some “environment”. • You have some notion of “good” behavior. COSC 425: Intro. to Machine Learning 30 30

  30. Case Studies COSC 425: Intro. to Machine Learning 31 31

  31. Case #1: OCR New Instance to Classify Instances Existing A Neural Network COSC 425: Intro. to Machine Learning 32 32

  32. Case #1: OCR Least Complex Most Complex https://en.wikipedia.org/wiki/MNIST_database COSC 425: Intro. to Machine Learning 33 33

  33. Case #1: OCR Machines can be fooled! Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images https://arxiv.org/abs/1412.1897 COSC 425: Intro. to Machine Learning 34 34

  34. Case #2: Computer Vision COSC 425: Intro. to Machine Learning 35 35

  35. Case #2: Computer Vision Deep Face : 97.35% vs Human : 97.53% https://arxiv.org/pdf/1804.06655.pdf COSC 425: Intro. to Machine Learning 36 36

  36. Case #2: Computer Vision COSC 425: Intro. to Machine Learning 37 37

  37. Case #3: Image Captioning ”Two pizzas on a stove with wine.” “Three men playing frisbee in the grass” COSC 425: Intro. to Machine Learning 38 38

  38. Case #3: Image Captioning “A refrigerator filled with lots of food and drinks. ”A yellow school bus”. COSC 425: Intro. to Machine Learning 39 39

  39. Case #4: Games March 2016 : AlphaGo defeats Lee Sedol. • “AlphaGo can’t beat me.” - Ke Jie (World Champion) • May 2017 : AlphaGo Master defeats Ke Jie • “Last year, AlphaGo was still quite humanlike when it • played. But this year, it has became like a god of Go”. Oct 2017 : AlphaGo Zero outperforms AlphaGo Master. • Key Point: No prior training based on human expertise. • COSC 425: Intro. to Machine Learning 40 40

  40. Case #5: Text Generation A Statistical Model of Language Text Corpus COSC 425: Intro. to Machine Learning 41 41

  41. Case #5: Text Generation General Pre-Trained Transformer-2 (GPT-2) This example uses arXiv-NLP’s training set. Try it here: https://transformer.huggingface.co/doc/arxiv-nlp COSC 425: Intro. to Machine Learning 42 42

  42. Case #5: Text Generation Writing HTML + CSS … via text-commands? GPT-3: Text Understanding OpenAI. Beta, Summer 2020. (Not available to the public.) COSC 425: Intro. to Machine Learning 43 43

  43. Case #5: Text Generation Qui Gon Jinn to Jar Jar Binks. (32 BBY) Problem : Machine learning hinges on prior data. COSC 425: Intro. to Machine Learning 44 44

  44. Grand Challenges COSC 425: Intro. to Machine Learning 45 45

  45. Today’s Machine Learning Machine Learning is Modern Computer Science Productivity Tools (e.g. Microsoft Word) • Well-Being Toos (e.g. Woebot) • Fraud Detection (e.g. CapitalOne, etc) • Speech Recognition (e.g. “Hey Google”) • … Why is Machine Learning Everywhere? Sensing + Devices à Explosion of Data • Hardware Advances à Explosion of Processing Capabilities • Democratized ML à Explosion of Resources, Frameworks, etc • The Era of AI à Companies, investors, start-ups, etc. • COSC 425: Intro. to Machine Learning 46 46

  46. Grand Challenge #1: Data O(n 2 ) algorithms are infeasible. ML has largely ignored algorithmic complexity. • A Need for Democratized Supercomputers. New techniques for processing large datasets. • A Need for Parallelization. Existing systems generally parallelize poorly (if at all). • COSC 425: Intro. to Machine Learning 47 47

  47. Grand Challenge #2: End-to-End Learning The ML pipeline is substantial. Efforts to streamline learning. • Single characters à Text Classification • https://arxiv.org/abs/1509.01626 Pixels à Autonomous Steering • https://arxiv.org/pdf/1604.07316v1.pdf COSC 425: Intro. to Machine Learning 48 48

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Introduction to Machine Learning ML-Basics: Components of Supervised Learning Learning goals

Introduction to Machine Learning ML-Basics: Components of Supervised Learning Learning goals

Introduction to Machine Learning ML-Basics: Components of Supervised Learning Learning goals Know the three components of a learner: Hypothesis space, risk, 6 = ( 1.7 , 1.3 ) T optimization 4 2 Understand that defining these R emp =

415 views • 9 slides
MACHINE LEARNING Probably Approximately Correct (PAC) Learning Alessandro Moschitti Department

MACHINE LEARNING Probably Approximately Correct (PAC) Learning Alessandro Moschitti Department

MACHINE LEARNING Probably Approximately Correct (PAC) Learning Alessandro Moschitti Department of Information Engineering and Computer Science University of Trento Email: moschitti@disi.unitn.it Objectives: defining a well defined statistical

442 views • 27 slides
An Exercise in An Exercise in Machine Learning Machine Learning

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 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

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: 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

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

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

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

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
1 Why Study Machine Learning? Why Study Machine Learning? Cognitive Science The Time is Ripe

1 Why Study Machine Learning? Why Study Machine Learning? Cognitive Science The Time is Ripe

What is Learning? Herbert Simon: Learning is any process by which a system improves performance from CS 391L: Machine Learning experience. Introduction What is the task? Classification Problem solving / planning /

603 views • 6 slides
MACHINE LEARNING, STATISTICAL LEARNING AND PARALLEL COMPUTING INTRODUCTION VS MACHINE LEARNING

MACHINE LEARNING, STATISTICAL LEARNING AND PARALLEL COMPUTING INTRODUCTION VS MACHINE LEARNING

JACOPO DI IORIO, MATTEO FONTANA, DANIELE OCCHIUTO, CLAUDIA VOLPETTI MACHINE LEARNING, STATISTICAL LEARNING AND PARALLEL COMPUTING INTRODUCTION VS MACHINE LEARNING STATISTICAL LEARNING Separate evolutions, but with shared methodologies MERGE

565 views • 55 slides
Apache PredictionIO End-to-End Machine Learning Server with Apache Spark What is Machine

Apache PredictionIO End-to-End Machine Learning Server with Apache Spark What is Machine

Apache PredictionIO End-to-End Machine Learning Server with Apache Spark What is Machine Learning? What is Machine Learning? Examples of machine learning applications: Facial recognition software E-mail spam detectors Automated

302 views • 17 slides
Machine Learning 11 AI Slides (6e) c Lin Zuoquan@PKU 1998-2020 11 1 11 Machine Learning

Machine Learning 11 AI Slides (6e) c Lin Zuoquan@PKU 1998-2020 11 1 11 Machine Learning

Machine Learning 11 AI Slides (6e) c Lin Zuoquan@PKU 1998-2020 11 1 11 Machine Learning 11.1 Learning agents 11.2 Inductive learning 11.3 Deep learning 11.4 Statistical learning 11.5 Reinforcement learning 11.6 Transfer learning

1.7k views • 159 slides
Deep Learning: Intro Juhan Nam Review of Traditional Machine Learning The traditional machine

Deep Learning: Intro Juhan Nam Review of Traditional Machine Learning The traditional machine

GCT634/AI613: Musical Applications of Machine Learning (Fall 2020) Deep Learning: Intro Juhan Nam Review of Traditional Machine Learning The traditional machine learning pipeline Temporal Frame-level Unsupervised Classifier Summary

613 views • 27 slides
Machine Learning for Auto Optimization What is Machine Learning? Definition: Machine

Machine Learning for Auto Optimization What is Machine Learning? Definition: Machine

Machine Learning for Auto Optimization What is Machine Learning? Definition: Machine learning refers to any system where the performance of a machine in performing a task improves by gaining more experience in performing that task .

394 views • 27 slides
MACHINE LEARNING kernels 1 MACHINE LEARNING 2012 MACHINE LEARNING Kernels: Intuition How

MACHINE LEARNING kernels 1 MACHINE LEARNING 2012 MACHINE LEARNING Kernels: Intuition How

MACHINE LEARNING 2012 MACHINE LEARNING MACHINE LEARNING kernels 1 MACHINE LEARNING 2012 MACHINE LEARNING Kernels: Intuition How to separate the red class from the grey class? x 2 360 r x 1 Polar coordinates Data

1.04k views • 44 slides
JAVA Java vs. Java Java Language Specification

JAVA Java vs. Java Java Language Specification

BR 10/05 JAVA Java vs. Java Java Language Specification http://java.sun.com/docs/books/jls/second_edition/html/j.title.doc.html Java programming language is compiled into java byte code Java Virtual Machine Specification

1.07k views • 44 slides
Supercomputing as a Service: Massively-Parallel Jobs on FaaS Platforms Sadjad Fouladi Stanford

Supercomputing as a Service: Massively-Parallel Jobs on FaaS Platforms Sadjad Fouladi Stanford

Supercomputing as a Service: Massively-Parallel Jobs on FaaS Platforms Sadjad Fouladi Stanford University Compiling clang takes >2 hours. https://xkcd.com/303/ R O T I D E "MY VIDEO'S ENCODING!" ENCODING! Compressing a

649 views • 33 slides
Tutorial: Intro to Java Getting started. 1 CS 349 - Java tutorial Background Designed by

Tutorial: Intro to Java Getting started. 1 CS 349 - Java tutorial Background Designed by

Tutorial: Intro to Java Getting started. 1 CS 349 - Java tutorial Background Designed by James Gosling Released by Sun Microsystems in 1995. Originally a proprietary license, but made open source under GNU GPL in 2007. Sun and

289 views • 14 slides
Aer Acceptance: Reasoning About System Outputs Dr. Stefanos Zachariadis @thenewstef

Aer Acceptance: Reasoning About System Outputs Dr. Stefanos Zachariadis @thenewstef

Aer Acceptance: Reasoning About System Outputs Dr. Stefanos Zachariadis @thenewstef https://moto.co.de https://cyclema.ps http://itv.com OUTLINE Issues not typically caught by a CI environment What we'd like to test aer the acceptance

670 views • 56 slides
Carsten Ziegeler

Carsten Ziegeler

Carsten Ziegeler cziegeler@apache.org Competence Center Open Source S&N AG, Germany Member of the Apache Software Foundation Committer in some Apache

1.81k views • 78 slides
Combinatory Categorial Grammar The effort to develop natural language grammars and

Combinatory Categorial Grammar The effort to develop natural language grammars and

Combinatory Categorial Grammar Goal Mildly-context sensitive grammar framework, with provable polynomial parseability To present the intuitions behind Combinatory Categorial Grammar as a framework for relating the structure of a linguistic

280 views • 13 slides
Welcome to INF1343! Database Modeling and Database Design Yuri Takhteyev University of Toronto

Welcome to INF1343! Database Modeling and Database Design Yuri Takhteyev University of Toronto

Welcome to INF1343! Database Modeling and Database Design Yuri Takhteyev University of Toronto January 3, 2011 This presentation is licensed under Creative Commons Attribution License, v. 3.0. To view a copy of this license, visit

1.2k views • 71 slides
CCT396, Fall 2011 Database Design and Implementation Yuri Takhteyev University of Toronto This

CCT396, Fall 2011 Database Design and Implementation Yuri Takhteyev University of Toronto This

CCT396, Fall 2011 Database Design and Implementation Yuri Takhteyev University of Toronto This presentation is licensed under Creative Commons Attribution License, v. 3.0. To view a copy of this license, visit

1.2k views • 71 slides

More recommend