practical unsupervised learning
play

Practical Unsupervised Learning INFO/CS 4300, Spring 2016 Jack - PowerPoint PPT Presentation

Sep 24, 2023 •439 likes •999 views

Practical Unsupervised Learning INFO/CS 4300, Spring 2016 Jack Hessel Unsupervised Learning is Cool! But how can we use this in our projects? 1. 2. But first, lets look at our dataset... Data Dimensionality! Probability of Lung Cancer

  1. Practical Unsupervised Learning INFO/CS 4300, Spring 2016 Jack Hessel

  2. Unsupervised Learning is Cool!

  3. But how can we use this in our projects? 1. 2.

  4. But first, let’s look at our dataset...

  5. Data Dimensionality! Probability of Lung Cancer Developing X X X X X X X X X Cigarettes Consumed Per Day

  6. Data Dimensionality! Probability of Lung Cancer Developing X X X X X X X X X Cigarettes Consumed Per Day

  7. Data Dimensionality! Probability of Lung X Cancer Developing X X X X X X X X Cigarettes Consumed Per Day

  8. Data Dimensionality! Probability of Lung X Cancer Developing X X X X X X X X Cigarettes Consumed Per Day

  9. Data Dimensionality! X Probability of Lung X Cancer Developing X X X X X X X X Cigarettes Consumed Per Day

  10. Data Dimensionality! Probability of Lung Cancer Developing X X X X X X X X X Cigarettes Consumed Per Day

  11. Data Dimensionality! Probability of Lung Cancer Developing X X X X X X X X X m o r f ? e t c h n g e i e r e h f Cigarettes Consumed f n i D a e m Per Day

  12. Data Dimensionality! 1 Dimension! Probability of Lung Cancer Developing X X X X X X X X X Cigarettes Consumed Per Day

  13. Words and documents are the same way... |D| X tfidf |V|

  14. Words and documents are the same way... |D| Pineapple X tfidf |V|

  15. Words and documents are the same way... |D| Pineapple X X tfidf |V|

  16. Words and documents are the same way... |D| Pineapple X X tfidf |V|

  17. Words and documents are the same way... |D| Pineapple X (but, really -- a low dimensional subspace…) X tfidf |V|

  18. Words and documents are the same way... e r e w s |D| e l p p a ” … e n d i e P l “ l a c e r X X tfidf |V|

  19. Words and documents are the same way... e r e w s |D| e l p p a ” … e n d i e P l “ l a c e r X X tfidf |V|

  20. Words and documents are the same way... e r e w s |D| e l p p a ” … e n d i e P l “ l a c e r X (but, really -- a low dimensional subspace…) X tfidf |V|

  21. Key questions in unsupervised NLP:

  22. Key questions in unsupervised NLP: 1. How many dimensions does our dataset actually live in?

  23. Key questions in unsupervised NLP: 1. How many dimensions does our dataset actually live in? 2. How do we project our data down to those dimensions?

  24. Key questions in unsupervised NLP: 1. How many dimensions does our dataset actually live in? 2. How do we project our data down to those dimensions? 3. Does any of this stuff actually do anything for our projects?

  25. Key tool in Linear Algebra, NLP, Machine Learning, Data Science, Computer Vision, Algorithms, Matrix Computations, Optimization, Statistics...

  26. Key tool in Linear Algebra, NLP, Machine Learning, Data Science, Computer Vision, Algorithms, Matrix Computations, Optimization, Statistics...

  27. Key tool in Linear Algebra, NLP, Machine Learning, Data Science, Computer Vision, Algorithms, Matrix Computations, Optimization, Statistics...

  28. Key tool in Linear Algebra, NLP, Machine Learning, Data Science, Computer Vision, Algorithms, Matrix Computations, Optimization, Statistics...

  29. |D| X tfidf |V| =

  30. |D| |D| 1 1 X tfidf |V| = |V|

  31. |D| |D| 1 1 X tfidf |V| = k |V|

  32. |D| |D| 1 1 k 1 1 X tfidf |V| = |V|

  33. |D| |D| 2 2 k 1 0 2 2 0 k 2 X tfidf |V| = |V|

  34. |D| |D| 2 2 k 1 0 2 2 0 k 2 X tfidf |V| = |V|

  36. Key questions in unsupervised NLP: 1. How many dimensions does our dataset actually live in? 2. How do we project our data down to those dimensions?

  37. Enough talk, time for some magic.

  38. |D| X tfidf + = |V|

  39. |D| X tfidf + = |V| Latent Semantic Indexing (LSI)

  40. |D| X tfidf + = |V| Latent Semantic Indexing (LSI) = Latent Semantic Analysis (LSA)

  41. As a side note... Great first NLP paper to read! Highly accessible :-) “Indexing by latent semantic analysis” - Deerwester et al. 1990 Scott Deerwester

  42. What are topic models? |D| |D| k k X tfidf |V| |V|

  43. What are topic models? |D| |D| k k X tfidf |V| |V| Latent semantic indexing (Deerwater et al. 1990)

  44. What are topic models? |D| |D| k k X tfidf |V| |V| Latent semantic indexing Non-negative matrix factorization (Deerwater et al. 1990) (Lee and Seung 1999)

  45. What are topic models? |D| |D| Latent dirichlet allocation k (Blei et al. 2003) k X tfidf |V| |V| Latent semantic indexing Non-negative matrix factorization (Deerwater et al. 1990) (Lee and Seung 1999)

  46. Why do we care?? |D| k k |V|

  47. Why do we care?? |D| k k |V|

  48. Why do we care?? |D| k k Interpretable, small number of features for |V| text classification!

  49. Why do we care?? |D| k k Interpretable, small number of features for |V| text classification!

  50. Document length *matters a lot*

  51. Document length *matters a lot* Different regimes of supervised NLP (Jack’s opinions only! Lots of caveats!)

  52. Document length *matters a lot* Different regimes of supervised NLP (Jack’s opinions only! Lots of caveats!) Less words More words 50-100 Words

  53. Document length *matters a lot* Different regimes of supervised NLP (Jack’s opinions only! Lots of caveats!) Topic models fail Topic models work Less words More words 50-100 Words

  54. Document length *matters a lot* Different regimes of supervised NLP (Jack’s opinions only! Lots of caveats!) Topic models fail Topic models work Less words More words 50-100 Words Naive bayes, n-gram features + linear classifier are almost always pretty good in practice :-)

  55. So can we see if our Kickstarter will be successful?

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

UNSUPERVISED LEARNING, CLUSTERING UNSUPERVISED LEARNING UNSUPERVISED LEARNING Supervised

UNSUPERVISED LEARNING, CLUSTERING UNSUPERVISED LEARNING UNSUPERVISED LEARNING Supervised

UNSUPERVISED LEARNING, CLUSTERING UNSUPERVISED LEARNING UNSUPERVISED LEARNING Supervised learning: X - y pairs, f(x) function approximation Unsupervised learning: only X, no y Exploring the space of X measurements,

440 views • 14 slides
Introduction to PCA Unsupervised Learning in R Unsupervised learning Two methods of

Introduction to PCA Unsupervised Learning in R Unsupervised learning Two methods of

UNSUPERVISED LEARNING IN R Introduction to PCA Unsupervised Learning in R Unsupervised learning Two methods of clustering finding groups of homogeneous items Next up, dimensionality reduction Find structure in features

904 views • 29 slides
Unsupervised Deep Learning Tutorial - Part 2 Alex Graves MarcAurelio Ranzato

Unsupervised Deep Learning Tutorial - Part 2 Alex Graves MarcAurelio Ranzato

Unsupervised Deep Learning Tutorial - Part 2 Alex Graves MarcAurelio Ranzato gravesa@google.com ranzato@fb.com NeurIPS, 3 December 2018 Overview Practical Recipes of Unsupervised Learning Learning representations Learning to

1.16k views • 103 slides
Unsupervised Learning and Clustering l In unsupervised learning you are given a data set with no

Unsupervised Learning and Clustering l In unsupervised learning you are given a data set with no

Unsupervised Learning and Clustering l In unsupervised learning you are given a data set with no output classifications (labels) l Clustering is an important type of unsupervised learning PCA was another type of unsupervised learning l The

858 views • 38 slides
Unsupervised Learning Unsupervised vs Supervised Learning: Most of this course focuses on

Unsupervised Learning Unsupervised vs Supervised Learning: Most of this course focuses on

Unsupervised Learning Unsupervised vs Supervised Learning: Most of this course focuses on supervised learning methods such as regression and classification. In that setting we observe both a set of features X 1 , X 2 , . . . , X p for each

934 views • 50 slides
Unsupervised Learning Unsupervised vs Supervised Learning: Most of this course focuses on

Unsupervised Learning Unsupervised vs Supervised Learning: Most of this course focuses on

Unsupervised Learning Unsupervised vs Supervised Learning: Most of this course focuses on supervised learning methods such as regression and classification. In that setting we observe both a set of features X 1 , X 2 , . . . , X p for each

721 views • 60 slides
Unsupervised Learning Andrea Passerini passerini@disi.unitn.it Machine Learning Unsupervised

Unsupervised Learning Andrea Passerini passerini@disi.unitn.it Machine Learning Unsupervised

Unsupervised Learning Andrea Passerini passerini@disi.unitn.it Machine Learning Unsupervised Learning Unsupervised Learning Setting Supervised learning requires the availability of labelled examples Labelling examples can be an extremely

752 views • 27 slides
12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from Wanli Ouyang, Zsolt Kira, Lawrence Neal, Raymond Yeh, Junting Lou and Teck-Yian Lim Unsupervised Learning in General Unsupervised learning is

1.48k views • 115 slides
Machine Learning for NLP Unsupervised Learning Aurlie Herbelot 2019 Centre for Mind/Brain

Machine Learning for NLP Unsupervised Learning Aurlie Herbelot 2019 Centre for Mind/Brain

Machine Learning for NLP Unsupervised Learning Aurlie Herbelot 2019 Centre for Mind/Brain Sciences University of Trento 1 Unsupervised learning In unsupervised learning, we learn without training data. The idea is to find a

998 views • 67 slides
Unsupervised Learning Introduction Nakul Verma Unsupervised Learning What can we learn from

Unsupervised Learning Introduction Nakul Verma Unsupervised Learning What can we learn from

Unsupervised Learning Introduction Nakul Verma Unsupervised Learning What can we learn from data when label information is not available? Supervised learning framework Supervised learning Data: Assumption: there is a (relatively simple)

442 views • 16 slides
Automatic Learning of a Morphological Model Theory and Unsupervised Approaches Unsupervised

Automatic Learning of a Morphological Model Theory and Unsupervised Approaches Unsupervised

Automatic Learning of a Morphological Model Theory and Unsupervised Approaches Unsupervised Learning - ToC Foundations Problem description General architecture Papers: Goldsmith 2001 and 2006 Goldsmith and Hu 2004

1.23k views • 43 slides
Unsupervised learning introduction October 7, 2019 Unsupervised learning introduction

Unsupervised learning introduction October 7, 2019 Unsupervised learning introduction

Unsupervised learning introduction October 7, 2019 Unsupervised learning introduction October 7, 2019 1 / 39 Intro General statement of the problem One has a set of N observations ( x 1 , x 2 , ..., x N ) of a random p -vector X having

495 views • 32 slides
Unsupervised learning General introduction to unsupervised learning PCA Special directions

Unsupervised learning General introduction to unsupervised learning PCA Special directions

Unsupervised learning General introduction to unsupervised learning PCA Special directions These are special directions we will try to find. Best direction u : |u| 2 = 1 2 1. Minimize : d i X i T u is the projection length x i u d i T

1.01k views • 29 slides
THE MAGIC OF UNSUPERVISED LEARNING Agustinus Nalwan Head of AI Carsales.com.au A LITTLE BIT

THE MAGIC OF UNSUPERVISED LEARNING Agustinus Nalwan Head of AI Carsales.com.au A LITTLE BIT

THE MAGIC OF UNSUPERVISED LEARNING Agustinus Nalwan Head of AI Carsales.com.au A LITTLE BIT ABOUT MYSELF AI 4 Years SAVING OUR FOREST BUSHFIRE DETECTION BACK TO THE MAIN TOPIC THE MAGIC OF UNSUPERVISED LEARNING SUPERVISED LEARNING

1.11k views • 82 slides
Clustering CS294 Practical Machine Learning Junming Yin 10/09/06 Outline Introduction

Clustering CS294 Practical Machine Learning Junming Yin 10/09/06 Outline Introduction

Clustering CS294 Practical Machine Learning Junming Yin 10/09/06 Outline Introduction Unsupervised learning What is clustering? Application Dissimilarity (similarity) of objects Clustering algorithm K-means, VQ,

649 views • 62 slides
Lecture 13: From Unsupervised to Reinforcement Learning (Chapters 8-10) R. Rao, 528: Lecture 13

Lecture 13: From Unsupervised to Reinforcement Learning (Chapters 8-10) R. Rao, 528: Lecture 13

CSE/NB 528 Lecture 13: From Unsupervised to Reinforcement Learning (Chapters 8-10) R. Rao, 528: Lecture 13 1 Todays Agenda: All about Learning F Unsupervised Learning Sparse Coding Predictive Coding F Supervised learning Perceptrons and

479 views • 24 slides
Squarelet Cooperative Learning Who We Are The Open Knowledge Foundation Germany (OKFN.de) is a

Squarelet Cooperative Learning Who We Are The Open Knowledge Foundation Germany (OKFN.de) is a

Squarelet Cooperative Learning Who We Are The Open Knowledge Foundation Germany (OKFN.de) is a nonprofit organization that advocates open knowledge, open data, transparency, and civil participation. Current education projects: edulabs.de

397 views • 19 slides
Fr Frequently uently as aske ked d questi stions ons il illu lust strate rated uCu

Fr Frequently uently as aske ked d questi stions ons il illu lust strate rated uCu

FAQ AQs: Fr Frequently uently as aske ked d questi stions ons il illu lust strate rated uCu Customs toms proje ject ct 05. 11. . 2014 th No 4 th Nove vembe mber r 201 2014 4 Disclaimer: All information in this document

627 views • 37 slides
DIVISION OF EXAMINATIONS, AWARDS AND SCHOLARSHIPS (DEAS) Sungai Long Campus (Ice, Cik Rita,

DIVISION OF EXAMINATIONS, AWARDS AND SCHOLARSHIPS (DEAS) Sungai Long Campus (Ice, Cik Rita,

DEAS DIVISION OF EXAMINATIONS, AWARDS AND SCHOLARSHIPS (DEAS) Sungai Long Campus (Ice, Cik Rita, Puan Farah) Kampar Campus (Mr. Iezwan, Mr. Yip) DEAS FIN FINANCIAL AID ANCIAL AID - Scholarships - Loans The purpose of the UTAR

1.04k views • 28 slides
2D1N Overseas Learning Journey to Malacca 2018 Group 1: 22 23 OCT 2018 Group 2: 24 25 OCT

2D1N Overseas Learning Journey to Malacca 2018 Group 1: 22 23 OCT 2018 Group 2: 24 25 OCT

2D1N Overseas Learning Journey to Malacca 2018 Group 1: 22 23 OCT 2018 Group 2: 24 25 OCT 2018 Group 3: 29 30 OCT 2018 General Information Evergreen Primary School GLOBAL INTERNATIONAL TRAVEL Address: 31 Woodlands Circle (Singapore

624 views • 41 slides
Beyond Cyber Securit ity Dangerous Toys USB Device Impersonators USB Killers Man in the

Beyond Cyber Securit ity Dangerous Toys USB Device Impersonators USB Killers Man in the

Beyond Cyber Securit ity Dangerous Toys USB Device Impersonators USB Killers Man in the Middle Faceplates Wireless Pineapples Payload Phone Chargers Dangerous Toys USB Device Impersonators USB Killers Man in the Middle Faceplates

626 views • 31 slides
Exploring Multivariate Data with Clustering and Dimensionality Reduction Marco Baroni Practical

Exploring Multivariate Data with Clustering and Dimensionality Reduction Marco Baroni Practical

Exploring Multivariate Data with Clustering and Dimensionality Reduction Marco Baroni Practical Statistics in R Outline Introduction Clustering Clustering in R Dimensionality reduction Dimensionality reduction in R Outline Introduction

773 views • 65 slides
Cyber@UC Meeting 56 W I F I If Youre New! Join our Slack: ucyber.slack.com SIGN IN!

Cyber@UC Meeting 56 W I F I If Youre New! Join our Slack: ucyber.slack.com SIGN IN!

Cyber@UC Meeting 56 W I F I If Youre New! Join our Slack: ucyber.slack.com SIGN IN! (Slackbot will post the link in #general) Feel free to get involved with one of our committees: Content Finance Public Affairs Outreach

456 views • 19 slides
Maximum Laplacian Energy among Threshold Graphs Christoph Helmberg (TU Chemnitz) joint work with

Maximum Laplacian Energy among Threshold Graphs Christoph Helmberg (TU Chemnitz) joint work with

introduction TG LE fixed n , m , f fixed n , m fixed n connected conclusion Maximum Laplacian Energy among Threshold Graphs Christoph Helmberg (TU Chemnitz) joint work with Vilmar Trevisan (UFRGS, Porto Alegre, Brasil) Laplacian Energy

470 views • 44 slides

More recommend