making friends w generative models
play

Making Friends w/ Generative Models How to make synthetic data for - PowerPoint PPT Presentation

Jul 02, 2023 •166 likes •806 views

Making Friends w/ Generative Models How to make synthetic data for sales, data science, development and testing Andrew Colombi, CTO @ Tonic, www.tonic.ai Framework Framework for Making Friends 1. Identify situations where data deficiency

  1. Making Friends w/ Generative Models How to make synthetic data for sales, data science, development and testing Andrew Colombi, CTO @ Tonic, www.tonic.ai

  8. Framework

  9. Framework for Making Friends 1. Identify situations where data deficiency occur 2. Target the right datasets 3. Toolbox of simple modeling techniques

  10. Identifying Data Deficiencies

  11. Identifying Data Deficiencies: Boundaries

  12. Identifying Data Deficiencies: Boundaries

  13. Identifying Data Deficiencies: Boundaries

  14. Identifying Data Deficiencies: Boundaries

  15. Identifying Data Deficiencies: Regulatory

  16. Identifying Data Deficiencies: Certification

  17. Identifying Data Deficiencies ● Boundaries ● Regulations ● Certification

  18. Targeting Datasets

  19. Targeting Datasets Target structured data.

  20. Mortgage Data Example

  28. Modeling

  29. Modeling: f(x) = x

  30. Modeling: Continuous Kernel Density Estimation

  31. Modeling: Kernel Density Estimation ● Models continuous variables ● Non-Parametric: Don’t need to specify distribution upfront ● Easy to extend to multiple dimensions ● Easy to implement

  32. Modeling: Kernel Density Estimation

  33. Modeling: Kernel Density Estimation

  34. Modeling: Kernel Density Estimation

  35. Modeling: Kernel Density Estimation

  36. Modeling: Kernel Density Estimation

  37. Modeling: Kernel Density Estimation ● Normal Distribution is a common kernel ● For K-dimensions use a K-dimensional kernel ● Sampling from a KDE: 1. Pick a random kernel 2. Sample randomly from that kernel ● (There is one parameter, the kernel width, which needs to be fit.)

  38. Modeling: Relational

  39. Modeling: Relational

  40. Modeling: Relational

  41. Modeling: Relational

  42. Modeling: Relational

  43. Modeling: Relational

  44. Modeling: Relational

  45. Modeling: Relational

  46. Modeling: Relational

  47. Modeling: Relational

  48. Modeling: Relational

  49. Modeling: Relational

  50. Modeling: Relational

  51. Modeling: Text

  52. Modeling: Text Jane Little (DOB: 9-6-1977) Jane Little seems to have had an inadequate response to treatment as yet. Symptoms of depression continue to be described. Her symptoms, as noted, are unchanged and they are just as frequent or intense as previously described. Jane Little describes feeling sad. Jane Little denies suicidal ideas or intentions. Jane Little reports the symptoms of this disorder continue unchanged. The subjective feeling of apprehension is occurring. Hypervigilance is occurring more frequently. Participant(s) Developing the Plan: - Susan Lobao (Counselor) - Mary Golden (Client) Diagnosis: - Major depressive disorder, single episode, severe without psychotic features, F32.2 (ICD-10) (Active) - Anxiety disorder, unspecified, F41.9 (ICD-10) (Active)

  53. Modeling: Text Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse eleifend justo nec purus vehicula, in tempus libero tristique. Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. In ultrices justo id urna ullamcorper laoreet. Curabitur dictum accumsan nunc, eu porttitor magna aliquet at. Ut faucibus, arcu quis condimentum sodales, erat tellus dapibus purus, in luctus sapien tellus at nisl. Duis convallis mattis mi, non pharetra diam commodo ac. Cras sit amet diam ac purus laoreet dignissim. Duis lectus diam, rutrum non vehicula ac, convallis non metus. Donec et luctus sem. Mauris nec erat volutpat, placerat ex ut, varius ipsum. In ultrices hendrerit nibh, id aliquet est. Maecenas vel turpis velit. Mauris ut faucibus lacus. Ut diam mi, ultrices vitae ante vitae, porttitor volutpat libero. Phasellus et nunc id tellus varius semper. Sed a euismod diam, id consequat risus. Donec vitae ornare magna. Nullam semper mi et magna suscipit posuere. Proin tincidunt leo augue, in facilisis turpis molestie ac. Sed convallis viverra massa et consectetur.

  54. Modeling: Text Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse eleifend justo nec purus vehicula, in tempus libero tristique. Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. In ultrices justo id urna ullamcorper laoreet. Curabitur dictum accumsan nunc, eu porttitor magna aliquet at. Ut faucibus, arcu quis condimentum sodales, erat tellus dapibus purus, in luctus sapien tellus at nisl. Duis convallis mattis mi, non pharetra diam commodo ac. Cras sit amet diam ac purus laoreet dignissim. Duis lectus diam, rutrum non vehicula ac, convallis non metus. Donec et luctus sem. Mauris nec erat volutpat, placerat ex ut, varius ipsum. In ultrices hendrerit nibh, id aliquet est. Maecenas vel turpis velit. Mauris ut faucibus lacus. Ut diam mi, ultrices vitae ante vitae, porttitor volutpat libero. Phasellus et nunc id tellus varius semper. Sed a euismod diam, id consequat risus. Donec vitae ornare magna. Nullam semper mi et magna suscipit posuere. Proin tincidunt leo augue, in facilisis turpis molestie ac. Sed convallis viverra massa et consectetur.

  55. Modeling: Text Jane Little (DOB: 9-6-1977) Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse eleifend justo nec purus vehicula, in tempus libero tristique. Pellentesque habitant morbi tristique Jane Little seems to have had an inadequate response to treatment as yet. senectus et netus et malesuada fames ac turpis egestas. In ultrices justo id urna Symptoms of depression continue to be described. Her symptoms, as noted, are unchanged and they are just as frequent or intense as ullamcorper laoreet. Curabitur dictum accumsan nunc, eu porttitor magna aliquet at. previously described. Jane Little describes feeling sad. Jane Little denies Ut faucibus, arcu quis condimentum sodales, erat tellus dapibus purus, in luctus suicidal ideas or intentions. Jane Little reports the symptoms of this sapien tellus at nisl. Duis convallis mattis mi, non pharetra diam commodo ac. Cras sit disorder continue unchanged. The subjective feeling of apprehension is amet diam ac purus laoreet dignissim. Duis lectus diam, rutrum non vehicula ac, occurring. Hypervigilance is occurring more frequently. convallis non metus. Donec et luctus sem. Mauris nec erat volutpat, placerat ex ut, Participant(s) Developing the Plan: varius ipsum. In ultrices hendrerit nibh, id aliquet est. Maecenas vel turpis velit. Mauris - Susan Lobao (Counselor) ut faucibus lacus. - Mary Golden (Client) Ut diam mi, ultrices vitae ante vitae, porttitor volutpat libero. Phasellus et nunc id tellus Diagnosis: varius semper. Sed a euismod diam, id consequat risus. Donec vitae ornare magna. - Major depressive disorder, single episode, severe without psychotic Nullam semper mi et magna suscipit posuere. Proin tincidunt leo augue, in facilisis features, F32.2 (ICD-10) (Active) - Anxiety disorder, unspecified, F41.9 (ICD-10) (Active) turpis molestie ac. Sed convallis viverra massa et consectetur.

  56. Modeling: Text Oclk Mjqqbu (BJF: 5-9-0435) Uhqw Cxidsp mjato xo avnq tvx ho zivoksdzic ygimegya pl bqrqlapuw bm spo. Yzhdfufb kl yirijkvuiw mirfdjci ch qf quoeyuvuf. Aff rcihlmgr, ks bpica, vrw zdutrxtem azn qmdl nab vxqb zu yszvvuzd ia clyllng zf rxbolwozuv zjbvyseui. Rgaj Ilbapp qiqqwhwwd nzgufii raq. Zsgs Yizrot cjvyke njsfnbvb hjkmv az ubkpwjpshx. Qida Ddhkau zzvcywe loy nwntiikj nu yqki wtsadfcb ufzufhra eddjkuuks. Usy wgwiongeee ijvlcit nd drmpunaybzhi im dfnjrgsbn. Vavuoyslqerphj qb vnoefwvzx rgoy chkberpztm. Zjnrerwwvwh(v) Tdxhzevwws dnn Xhod: - Sbbca Purfr (Iavkrrgog) - Ewrk Ewqgfa (Dhkitc) Vftsocqum: - Nwbhm vhjajgbqxf kjprbkxs, civlnv scgxyqz, oysewy jymbein hfmysbpez zqktnhha, D72.2 (VKW-41) (Motpgr) - Dznnphf wbvpycuc, kbrlymbhmuq, L55.0 (LJT-92) (Uzursy)

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 Generative Models (and GANs) Haoqiang Fan fhq@megvii.com Nov. 2017 Figures

Introduction to Generative Models (and GANs) Haoqiang Fan fhq@megvii.com Nov. 2017 Figures

Introduction to Generative Models (and GANs) Haoqiang Fan fhq@megvii.com Nov. 2017 Figures adapted from NIPS 2016 Tutorial Generative Adversarial Networks Generative Models: Learning the Distributions Discriminative: learns the likelihood

1.37k views • 77 slides
Probabilistic Models of Cognition: Generative models Table of Contents Chapter

Probabilistic Models of Cognition: Generative models Table of Contents Chapter

Probabilistic Models of Cognition: Generative models Table of Contents Chapter Content Generative Model Example: Plinko Machine Working Model can be used captures some for simulation structure of the world in useful way

825 views • 78 slides
Adversarial BoltzmannMachines Belief Nets Networks Variational NADE

Adversarial BoltzmannMachines Belief Nets Networks Variational NADE

Unsupervised Learning Non-probabilistic Models Probabilistic Sparse Coding (Generative) Models Autoencoders Others (e.g. k-means) Tractable Models Non-Tractable Models Generative Fully observed Adversarial

815 views • 58 slides
Classification with generative models 2 DSE 210 Classification with parametrized models

Classification with generative models 2 DSE 210 Classification with parametrized models

Classification with generative models 2 DSE 210 Classification with parametrized models Classifiers with a fixed number of parameters can represent a limited set of functions. Learning a model is about picking a good approximation. Typically the

427 views • 39 slides
Deep Generative models for Inverse Problems Alex Dimakis joint work with Ashish Bora, Dave Van

Deep Generative models for Inverse Problems Alex Dimakis joint work with Ashish Bora, Dave Van

Deep Generative models for Inverse Problems Alex Dimakis joint work with Ashish Bora, Dave Van Veen and Ajil Jalal, Sriram Vishwanath and Eric Price, UT Austin Outline Generative Models Using generative models for Inverse

1.17k views • 101 slides
Augmented Statistical Models: Exploiting Generative Models in Discriminative Classifiers Martin

Augmented Statistical Models: Exploiting Generative Models in Discriminative Classifiers Martin

Augmented Statistical Models: Exploiting Generative Models in Discriminative Classifiers Martin Layton & Mark Gales 9 December 2005 Cambridge University Engineering Department NIPS 2005 Augmented Statistical Models: Exploiting Generative

726 views • 25 slides
Invertible Generative Models for Inverse Problems Mitigating Representation Error and Dataset Bias

Invertible Generative Models for Inverse Problems Mitigating Representation Error and Dataset Bias

Invertible Generative Models for Inverse Problems Mitigating Representation Error and Dataset Bias M. Asim, M. Daniels, O. Leong, P . Hand, A. Ahmed Inverse Problems with Generative Models as Image Priors Inverse Problems with Generative Models

369 views • 22 slides
Modals, conditionals, and probabilistic generative models Topic 1: intro to probability &

Modals, conditionals, and probabilistic generative models Topic 1: intro to probability &

Modals, conditionals, and probabilistic generative models Topic 1: intro to probability & generative models; a bit on modality Dan Lassiter, Stanford Linguistics Universit de Paris VII, 25/11/19 4 lectures: The plan 1. probability,

694 views • 56 slides
LEARNING GENERATIVE MODELS ACROSS INCOMPARABLE SPACES Cha harlot otte Bunne unne , David

LEARNING GENERATIVE MODELS ACROSS INCOMPARABLE SPACES Cha harlot otte Bunne unne , David

LEARNING GENERATIVE MODELS ACROSS INCOMPARABLE SPACES Cha harlot otte Bunne unne , David Alvarez-Melis, Andreas Krause, Stefanie Jegelka Pos oster #173 173 Poster #173 173 & Charlotte Bunne Generative Modeling generative = network

250 views • 13 slides
Detecting Communities of Commuters: Graph Based Techniques vs Generative Models Ashish Dandekar,

Detecting Communities of Commuters: Graph Based Techniques vs Generative Models Ashish Dandekar,

Detecting Communities of Commuters: Graph Based Techniques vs Generative Models Ashish Dandekar, St ephane Bressan, Talel Abdessalem, Huayu Wu, Wee Siong Ng September 7, 2016 1 Introduction Related Work Generative Models Experiments

786 views • 44 slides
Outline Latent Variable Generative Models Cooperative Vector Quantizer Model Model

Outline Latent Variable Generative Models Cooperative Vector Quantizer Model Model

2/4/2020 CS 3750 Advanced Machine Learning Latent Variable Generative Models II Ahmad Diab AHD23@cs.pitt.edu Feb 4, 2020 Based on slides of Professor Milos Hauskrecht Outline Latent Variable Generative Models Cooperative Vector

435 views • 20 slides
Learning the Structure of Generative Models without Labeled Data Stephen Bach Bryan He

Learning the Structure of Generative Models without Labeled Data Stephen Bach Bryan He

Learning the Structure of Generative Models without Labeled Data Stephen Bach Bryan He Alex Ratner Chris R Stanford University This Talk We study structure learning for generative models in which a latent variable

599 views • 33 slides
Modals, conditionals, and probabilistic generative models Topic 2: Indicative conditionals

Modals, conditionals, and probabilistic generative models Topic 2: Indicative conditionals

Modals, conditionals, and probabilistic generative models Topic 2: Indicative conditionals Separating semantics from reasoning Dan Lassiter, Stanford Linguistics Universit de Paris VII, 2/12/19 Overall plan 1. probability, generative

997 views • 52 slides
CSC 411: Lecture 08: Generative Models for Classification Class based on Raquel Urtasun &

CSC 411: Lecture 08: Generative Models for Classification Class based on Raquel Urtasun &

CSC 411: Lecture 08: Generative Models for Classification Class based on Raquel Urtasun & Rich Zemels lectures Sanja Fidler University of Toronto Feb 5, 2016 Urtasun, Zemel, Fidler (UofT) CSC 411: 08-Generative Models Feb 5, 2016 1 /

475 views • 23 slides
Probability Functional Descent: A Unifying Perspective on GANs, VI, and RL Casey Chu <

Probability Functional Descent: A Unifying Perspective on GANs, VI, and RL Casey Chu <

Probability Functional Descent: A Unifying Perspective on GANs, VI, and RL Casey Chu < caseychu@stanford.edu > Jose Blanchet Peter Glynn Deep generative models Deep generative models Variational inference Deep generative models

275 views • 16 slides
Generative Models Jo ao Paulo Papa and Marcos Cleison Silva Santana December 17, 2019 UNESP -

Generative Models Jo ao Paulo Papa and Marcos Cleison Silva Santana December 17, 2019 UNESP -

Generative Models Jo ao Paulo Papa and Marcos Cleison Silva Santana December 17, 2019 UNESP - S ao Paulo State University School of Sciences, Departament of Computing Bauru, SP - Brazil Outline 1. Generative versus Discriminative Models

513 views • 28 slides
On behavioral complementarity and its implications Chris Chambers, Federico Echenique, and Eran

On behavioral complementarity and its implications Chris Chambers, Federico Echenique, and Eran

On behavioral complementarity and its implications Chris Chambers, Federico Echenique, and Eran Shmaya California Institute of Technology UPenn March 18, 2008 Complementary goods Complementary goods Coffee and Sugar Tea and Lemon Peanut

751 views • 56 slides
Visualizing the Semantic Structure in Classical Music Works Winnie Wing-Yi Chan Supervised by

Visualizing the Semantic Structure in Classical Music Works Winnie Wing-Yi Chan Supervised by

Visualizing the Semantic Structure in Classical Music Works Winnie Wing-Yi Chan Supervised by Dr. Huamin Qu MPhil Thesis Defense Examination Department of Computer Science and Engineering The Hong Kong University of Science and Technology

892 views • 63 slides
TheGameTheoreticWeb TheGameTheoreticWeb

TheGameTheoreticWeb TheGameTheoreticWeb

TheGameTheoreticWeb TheGameTheoreticWeb Web(2.0)Mining:AnalyzingSocial Web(2.0)Mining:AnalyzingSocial Media Media AnupamJoshi AnupamJoshi

969 views • 80 slides
BBNANG243 Phonological analysis Prosody: Phrase stress, rhythm & intonation Zoltn G.

BBNANG243 Phonological analysis Prosody: Phrase stress, rhythm & intonation Zoltn G.

BBNANG243 Phonological analysis Prosody: Phrase stress, rhythm & intonation Zoltn G. Kiss, Pter Szigetvri, Mikls Trkenczy Dept. of English Linguistics, Etvs Lornd University z. g. kiss (elte|delg) analysis | prosody 1

660 views • 43 slides
Peer-to-Peer Networks 16 P2P in the Wild Christian Ortolf Technical Faculty Computer-Networks

Peer-to-Peer Networks 16 P2P in the Wild Christian Ortolf Technical Faculty Computer-Networks

Peer-to-Peer Networks 16 P2P in the Wild Christian Ortolf Technical Faculty Computer-Networks and Telematics University of Freiburg Real-World P2P Applications in 2016 File sharing & transmission Bittorrent, eMule, FastTrack,

604 views • 10 slides
Chapter 1: Theatre and History history Webster: "the branch of knowledge that deals

Chapter 1: Theatre and History history Webster: "the branch of knowledge that deals

Chapter 1: Theatre and History history Webster: "the branch of knowledge that deals systematically with the past" Henry Ford: "more or less bunk" anonymous student: "one damn thing after another"

247 views • 20 slides
What are the most likely pathophysiological mechanisms involved in HFpEF? Carolyn S.P. Lam, MD

What are the most likely pathophysiological mechanisms involved in HFpEF? Carolyn S.P. Lam, MD

What are the most likely pathophysiological mechanisms involved in HFpEF? Carolyn S.P. Lam, MD National Heart Centre Singapore, Singapore HFpEF Lam, Voors, de Boer, Solomon, van Veldhuisen Eur Heart J 2018 Hemodynamic targets Lam, Voors, de

583 views • 20 slides
Children and Oral H ealth February 9, 2017 2:00 p.m. EST Agenda Overview and Introductions

Children and Oral H ealth February 9, 2017 2:00 p.m. EST Agenda Overview and Introductions

Advocating for H ealthy Smiles: Children and Oral H ealth February 9, 2017 2:00 p.m. EST Agenda Overview and Introductions Addressing the Issue: Connecting Children Enrolled in Medicaid and CHIP with Oral Healthcare Promoting the

643 views • 61 slides

More recommend