fast uncertainty estimates and bayesian model averaging
play

FAST UNCERTAINTY ESTIMATES AND BAYESIAN MODEL AVERAGING OF DNNS - PowerPoint PPT Presentation

May 30, 2023 •107 likes •301 views

1 FAST UNCERTAINTY ESTIMATES AND BAYESIAN MODEL AVERAGING OF DNNS WESLEY MADDOX JOINT WORK WITH TIMUR GARIPOV , PAVEL IZMAILOV , DMITRY VETROV , ANDREW GORDON WILSON 2 SUMMARY Stochastic Weight Averaging (Izmailov et al, UAI,

  1. � 1 FAST UNCERTAINTY ESTIMATES AND BAYESIAN MODEL AVERAGING OF DNNS WESLEY MADDOX JOINT WORK WITH TIMUR GARIPOV , PAVEL IZMAILOV , DMITRY VETROV , ANDREW GORDON WILSON

  2. � 2 SUMMARY ‣ Stochastic Weight Averaging (Izmailov et al, UAI, 2018) computes first moment of weights given from SGD iterates with a modified learning rate schedule. ‣ We propose to keep the variance as well to form a Gaussian approximation in weight space. ‣ Sample from Gaussian to compute Bayesian model averages and estimate uncertainty. ‣ Theoretically motivated from results on SGD & relation of iterates to Gaussian distribution (Ruppert, 1992 and Mandt et al, 2017).

  3. <latexit sha1_base64="uGLxWtCmfm/tnJsHfMg2JigS3sc=">ACBnicbVDLSgNBEJyNrxhfqx5FGAxCAhJ2RdBj0IsniWgekF3C7GSDJndHWZ6xSXm5MVf8eJBEa9+gzf/xsnjoIkFDUVN91dgRcg+N8W5mFxaXlexqbm19Y3PL3t6p6ThRlFVpLGLVCIhmgkesChwEa0jFSBgIVg/6FyO/fseU5nF0C6lkfki6Ee9wSsBILXtfFjzoMSAPaRF7REoV3+OrghcmR/im2LzTskZA8Td0ryaIpKy/7y2jFNQhYBFUTrputI8AdEAaeCDXNeopktE+6rGloREKm/cH4jSE+NEobd2JlKgI8Vn9PDEiodRoGpjMk0NOz3kj8z2sm0DnzBzySCbCIThZ1EoEhxqNMcJsrRkGkhCquLkV0x5RhIJLmdCcGdfnie145LrlNzrk3z5fBpHFu2hA1RALjpFZXSJKqiKHpEz+gVvVlP1ov1bn1MWjPWdGYX/YH1+QM4sZen</latexit> <latexit sha1_base64="uGLxWtCmfm/tnJsHfMg2JigS3sc=">ACBnicbVDLSgNBEJyNrxhfqx5FGAxCAhJ2RdBj0IsniWgekF3C7GSDJndHWZ6xSXm5MVf8eJBEa9+gzf/xsnjoIkFDUVN91dgRcg+N8W5mFxaXlexqbm19Y3PL3t6p6ThRlFVpLGLVCIhmgkesChwEa0jFSBgIVg/6FyO/fseU5nF0C6lkfki6Ee9wSsBILXtfFjzoMSAPaRF7REoV3+OrghcmR/im2LzTskZA8Td0ryaIpKy/7y2jFNQhYBFUTrputI8AdEAaeCDXNeopktE+6rGloREKm/cH4jSE+NEobd2JlKgI8Vn9PDEiodRoGpjMk0NOz3kj8z2sm0DnzBzySCbCIThZ1EoEhxqNMcJsrRkGkhCquLkV0x5RhIJLmdCcGdfnie145LrlNzrk3z5fBpHFu2hA1RALjpFZXSJKqiKHpEz+gVvVlP1ov1bn1MWjPWdGYX/YH1+QM4sZen</latexit> <latexit sha1_base64="uGLxWtCmfm/tnJsHfMg2JigS3sc=">ACBnicbVDLSgNBEJyNrxhfqx5FGAxCAhJ2RdBj0IsniWgekF3C7GSDJndHWZ6xSXm5MVf8eJBEa9+gzf/xsnjoIkFDUVN91dgRcg+N8W5mFxaXlexqbm19Y3PL3t6p6ThRlFVpLGLVCIhmgkesChwEa0jFSBgIVg/6FyO/fseU5nF0C6lkfki6Ee9wSsBILXtfFjzoMSAPaRF7REoV3+OrghcmR/im2LzTskZA8Td0ryaIpKy/7y2jFNQhYBFUTrputI8AdEAaeCDXNeopktE+6rGloREKm/cH4jSE+NEobd2JlKgI8Vn9PDEiodRoGpjMk0NOz3kj8z2sm0DnzBzySCbCIThZ1EoEhxqNMcJsrRkGkhCquLkV0x5RhIJLmdCcGdfnie145LrlNzrk3z5fBpHFu2hA1RALjpFZXSJKqiKHpEz+gVvVlP1ov1bn1MWjPWdGYX/YH1+QM4sZen</latexit> <latexit sha1_base64="uGLxWtCmfm/tnJsHfMg2JigS3sc=">ACBnicbVDLSgNBEJyNrxhfqx5FGAxCAhJ2RdBj0IsniWgekF3C7GSDJndHWZ6xSXm5MVf8eJBEa9+gzf/xsnjoIkFDUVN91dgRcg+N8W5mFxaXlexqbm19Y3PL3t6p6ThRlFVpLGLVCIhmgkesChwEa0jFSBgIVg/6FyO/fseU5nF0C6lkfki6Ee9wSsBILXtfFjzoMSAPaRF7REoV3+OrghcmR/im2LzTskZA8Td0ryaIpKy/7y2jFNQhYBFUTrputI8AdEAaeCDXNeopktE+6rGloREKm/cH4jSE+NEobd2JlKgI8Vn9PDEiodRoGpjMk0NOz3kj8z2sm0DnzBzySCbCIThZ1EoEhxqNMcJsrRkGkhCquLkV0x5RhIJLmdCcGdfnie145LrlNzrk3z5fBpHFu2hA1RALjpFZXSJKqiKHpEz+gVvVlP1ov1bn1MWjPWdGYX/YH1+QM4sZen</latexit> <latexit sha1_base64="Mf9KAZJ8VrK1OBmaJH2lqNu3TI=">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</latexit> <latexit sha1_base64="Mf9KAZJ8VrK1OBmaJH2lqNu3TI=">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</latexit> <latexit sha1_base64="Mf9KAZJ8VrK1OBmaJH2lqNu3TI=">ACMHicbZDLSgMxFIYz3q23qks3wSK0qGVGBF16WagLpYJVoVPLmTS1wcxMSM6IZewjufFRdKOgiFufwrTOwtsPgZ/vnMPJ+QMlhUHXfXYGBoeGR0bHxnMTk1PTM/nZuVMTJ5rxKotlrM8DMFyKiFdRoOTnSnMIA8nPgqvdXv3smsj4ugEO4rXQ7iMREswQIsa+T1V9LHNEW47JeqDUjq+oUcZa6SH25XuCi3u/wAlukx9aXc0gR6ULtJVr1tq5Atu2e2L/jVeZgokU6WRf/CbMUtCHiGTYEzNcxXWU9AomOTdnJ8YroBdwSWvWRtByE097R/cpUuWNGkr1vZFSPv0+0QKoTGdMLCdIWDb/K714H+1WoKtzXoqIpUgj9jXolYiKca0lx5tCs0Zyo41wLSwf6WsDRoY2oxzNgTv98l/zela2XPL3vF6YWsni2OMLJBFUiQe2SBbZJ9USJUwckceyQt5de6dJ+fNef9qHXCymXnyQ87HJ0gRpzc=</latexit> <latexit sha1_base64="Mf9KAZJ8VrK1OBmaJH2lqNu3TI=">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</latexit> <latexit sha1_base64="tR6QRGiHr0gv/IN6f3L8/n2xj4c=">ACEHicbVDLSgMxFM34rPVdekmWMTWRZkRQTdCUQSXFewD2jpk0rQNzcyE5I4wTPsJbvwVNy4UcevSnX9j2s5CWw9cODnXnLv8aTgGmz721pYXFpeWc2sZdc3Nre2czu7NR1GirIqDUWoGh7RTPCAVYGDYA2pGPE9were4Grs1x+Y0jwM7iCWrO2TXsC7nBIwkps7koX4/ngYF/EFvnYTWhBnwExwqhgrOH0WSy6ubxdsifA8RJSR6lqLi5r1YnpJHPAqCaN10bAnthCjgVLBRthVpJgkdkB5rGhoQn+l2MjlohA+N0sHdUJkKAE/U3xMJ8bWOfc90+gT6etYbi/95zQi65+2EBzICFtDpR91IYAjxOB3c4YpRELEhCpudsW0TxShYDLMmhCc2ZPnSe2k5Ngl5/Y0X75M48igfXSACshBZ6iMblAFVRFj+gZvaI368l6sd6tj2nrgpXO7KE/sD5/AITVm6I=</latexit> <latexit sha1_base64="tR6QRGiHr0gv/IN6f3L8/n2xj4c=">ACEHicbVDLSgMxFM34rPVdekmWMTWRZkRQTdCUQSXFewD2jpk0rQNzcyE5I4wTPsJbvwVNy4UcevSnX9j2s5CWw9cODnXnLv8aTgGmz721pYXFpeWc2sZdc3Nre2czu7NR1GirIqDUWoGh7RTPCAVYGDYA2pGPE9were4Grs1x+Y0jwM7iCWrO2TXsC7nBIwkps7koX4/ngYF/EFvnYTWhBnwExwqhgrOH0WSy6ubxdsifA8RJSR6lqLi5r1YnpJHPAqCaN10bAnthCjgVLBRthVpJgkdkB5rGhoQn+l2MjlohA+N0sHdUJkKAE/U3xMJ8bWOfc90+gT6etYbi/95zQi65+2EBzICFtDpR91IYAjxOB3c4YpRELEhCpudsW0TxShYDLMmhCc2ZPnSe2k5Ngl5/Y0X75M48igfXSACshBZ6iMblAFVRFj+gZvaI368l6sd6tj2nrgpXO7KE/sD5/AITVm6I=</latexit> <latexit sha1_base64="tR6QRGiHr0gv/IN6f3L8/n2xj4c=">ACEHicbVDLSgMxFM34rPVdekmWMTWRZkRQTdCUQSXFewD2jpk0rQNzcyE5I4wTPsJbvwVNy4UcevSnX9j2s5CWw9cODnXnLv8aTgGmz721pYXFpeWc2sZdc3Nre2czu7NR1GirIqDUWoGh7RTPCAVYGDYA2pGPE9were4Grs1x+Y0jwM7iCWrO2TXsC7nBIwkps7koX4/ngYF/EFvnYTWhBnwExwqhgrOH0WSy6ubxdsifA8RJSR6lqLi5r1YnpJHPAqCaN10bAnthCjgVLBRthVpJgkdkB5rGhoQn+l2MjlohA+N0sHdUJkKAE/U3xMJ8bWOfc90+gT6etYbi/95zQi65+2EBzICFtDpR91IYAjxOB3c4YpRELEhCpudsW0TxShYDLMmhCc2ZPnSe2k5Ngl5/Y0X75M48igfXSACshBZ6iMblAFVRFj+gZvaI368l6sd6tj2nrgpXO7KE/sD5/AITVm6I=</latexit> <latexit sha1_base64="tR6QRGiHr0gv/IN6f3L8/n2xj4c=">ACEHicbVDLSgMxFM34rPVdekmWMTWRZkRQTdCUQSXFewD2jpk0rQNzcyE5I4wTPsJbvwVNy4UcevSnX9j2s5CWw9cODnXnLv8aTgGmz721pYXFpeWc2sZdc3Nre2czu7NR1GirIqDUWoGh7RTPCAVYGDYA2pGPE9were4Grs1x+Y0jwM7iCWrO2TXsC7nBIwkps7koX4/ngYF/EFvnYTWhBnwExwqhgrOH0WSy6ubxdsifA8RJSR6lqLi5r1YnpJHPAqCaN10bAnthCjgVLBRthVpJgkdkB5rGhoQn+l2MjlohA+N0sHdUJkKAE/U3xMJ8bWOfc90+gT6etYbi/95zQi65+2EBzICFtDpR91IYAjxOB3c4YpRELEhCpudsW0TxShYDLMmhCc2ZPnSe2k5Ngl5/Y0X75M48igfXSACshBZ6iMblAFVRFj+gZvaI368l6sd6tj2nrgpXO7KE/sD5/AITVm6I=</latexit> � 3 APPROXIMATE BAYESIAN INFERENCE ‣ Why? ‣ Compute intractable integrals p ( y ∗ | y ) = E p ( θ | y ) ( p ( y | θ )) ‣ Uncertainty quantification ‣ How? ‣ Laplace: p ( θ | y ) ≈ N ( θ MAP , ( H ( θ MAP ) + λ I ) − 1 ) ‣ Variational Bayes: p ( θ | y ) ≈ N ( µ, S ) ‣ Markov Chain Monte Carlo

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

Bayesian model averaging Dr. Jarad Niemi STAT 544 - Iowa State University March 9, 2017 Jarad

Bayesian model averaging Dr. Jarad Niemi STAT 544 - Iowa State University March 9, 2017 Jarad

Bayesian model averaging Dr. Jarad Niemi STAT 544 - Iowa State University March 9, 2017 Jarad Niemi (STAT544@ISU) Bayesian model averaging March 9, 2017 1 / 27 Outline Bayesian model averaging BIC model averaging Model search Parameter

384 views • 27 slides
Bayesian Model Selection and Averaging Nonlinear Models Bayes factors Example Families FFX

Bayesian Model Selection and Averaging Nonlinear Models Bayes factors Example Families FFX

Bayesian Model Selection and Averaging Will Penny Model Comparison Model Evidence Complexity Bayesian Model Selection and Averaging Nonlinear Models Bayes factors Example Families FFX Model Will Penny Inference RFX Model Inference

600 views • 59 slides
MCMC based machine learning a . (Bayesian Model Averaging) Nicos Angelopoulos

MCMC based machine learning a . (Bayesian Model Averaging) Nicos Angelopoulos

MCMC based machine learning a . (Bayesian Model Averaging) Nicos Angelopoulos n.angelopoulos@ed.ac.uk School of Biological Sciences Biochemistry Group University of Edinburgh, Scotland, UK. a Collaborative work with James Cussens, York

393 views • 21 slides
Bayesian model averaging Dr. Jarad Niemi Iowa State University September 7, 2017 Jarad Niemi

Bayesian model averaging Dr. Jarad Niemi Iowa State University September 7, 2017 Jarad Niemi

Bayesian model averaging Dr. Jarad Niemi Iowa State University September 7, 2017 Jarad Niemi (Iowa State) Bayesian model averaging September 7, 2017 1 / 30 Bayesian model averaging Bayesian model averaging Let { M : } indicate

423 views • 30 slides
STAT 339 Hidden Markov Models III 21 April 2017 Bayesian Estimation / Model Averaging Outline

STAT 339 Hidden Markov Models III 21 April 2017 Bayesian Estimation / Model Averaging Outline

STAT 339 Hidden Markov Models III 21 April 2017 Bayesian Estimation / Model Averaging Outline Inference Tasks in HMM Efficient Marginalization The Forward-Backward Algorithm Max Likelihood Parameter Estimation EM for HMMs EM Summary Gibbs

1.08k views • 38 slides
A Simple Bayesian Game Prediction Model By: Jake Flancer The Motivation Quantify Team

A Simple Bayesian Game Prediction Model By: Jake Flancer The Motivation Quantify Team

A Simple Bayesian Game Prediction Model By: Jake Flancer The Motivation Quantify Team Performance With Uncertainty Estimates Using Limited Data 2 Bayesian Statistics Incorporating beliefs not in data Prior padding data +

847 views • 28 slides
Obtaining first place estimates for Model 1 James Ritchie (and Iain Murray) Bayesian Inference

Obtaining first place estimates for Model 1 James Ritchie (and Iain Murray) Bayesian Inference

Obtaining first place estimates for Model 1 James Ritchie (and Iain Murray) Bayesian Inference Bayes' rule: Prior Likelihood Posterior Bayesian Inference Approximate with S samples drawn from Priors Need to choose Read the

565 views • 22 slides
Using Bayesian Model Probability with ensemble methods to quantify uncertainty in reservoir

Using Bayesian Model Probability with ensemble methods to quantify uncertainty in reservoir

Using Bayesian Model Probability with ensemble methods to quantify uncertainty in reservoir modelling with multiple prior scenarios Sigurd Ivar Aanonsen, NORCE Energy Svenn Tveit, NORCE Energy Mathias Alerini, Equinor ASA EnKF Workshop, Voss,

473 views • 43 slides
Fast Quantification of Uncertainty and Robustness with Variational Bayes Tamara Broderick ITT

Fast Quantification of Uncertainty and Robustness with Variational Bayes Tamara Broderick ITT

Fast Quantification of Uncertainty and Robustness with Variational Bayes Tamara Broderick ITT Career Development Assistant Professor, MIT With: Ryan Giordano, Rachael Meager, Jonathan H. Huggins, Michael I. Jordan Bayesian inference

1.84k views • 170 slides
Outline Intro to RL and Bayesian Learning History of Bayesian RL Model-based Bayesian

Outline Intro to RL and Bayesian Learning History of Bayesian RL Model-based Bayesian

Outline Intro to RL and Bayesian Learning History of Bayesian RL Model-based Bayesian RL Prior knowledge, policy optimization, discussion, Bayesian approaches for other RL variants Model-free Bayesian RL Gaussian

1.23k views • 63 slides
Fast Bayesian automatic Fast Bayesian automatic adaptive quadrature adaptive quadrature Gh.

Fast Bayesian automatic Fast Bayesian automatic adaptive quadrature adaptive quadrature Gh.

Fast Bayesian automatic Fast Bayesian automatic adaptive quadrature adaptive quadrature Gh. Adam, S. Adam LIT-JINR Dubna, Russia &amp; IFIN-HH Bucharest, Romania Invited Lecture at the RO-LCG 2014 conference, November 3-5, 2014 Outline

551 views • 52 slides
Uncertainty quantification of Antarctic contribution to sea-level rise using the fast Elementary

Uncertainty quantification of Antarctic contribution to sea-level rise using the fast Elementary

European Geosciences Union General Assembly 2017 Uncertainty quantification of Antarctic contribution to sea-level rise using the fast Elementary Thermomechanical Ice Sheet (f.ETISh) model K. Bulthuis 1 , 2 , M. Arnst 1 , F. Pattyn 2 , L. Favier 2

647 views • 28 slides
Value Averaging I nvesting The Strategy for Enhancing Investment Returns What is Value Averaging?

Value Averaging I nvesting The Strategy for Enhancing Investment Returns What is Value Averaging?

Value Averaging I nvesting The Strategy for Enhancing Investment Returns What is Value Averaging? It is a combination of Dollar Cost Averaging and Portfolio Rebalancing It is an averaging technique where the portfolio value increases in a

306 views • 27 slides
Uncertainty 10 AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 10 1 10 Uncertainty 10.1

Uncertainty 10 AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 10 1 10 Uncertainty 10.1

Uncertainty 10 AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 10 1 10 Uncertainty 10.1 Uncertainty 10.2 Probability Syntax and semantics Inference Independence Bayes rule 10.3 Bayesian networks 10.4 Probabilistic reasoning

1.38k views • 102 slides
1 Estimation from outbreaks when R 0 &lt; 1 Estimating R 0 : from epidemic data If case data are

1 Estimation from outbreaks when R 0 &lt; 1 Estimating R 0 : from epidemic data If case data are

Outline Parameter estimation, uncertainty, Estimating R 0 model fitting, model selection, Parameter estimation - Likelihood approaches and sensitivity and uncertainty analysis - Bayesian approaches Fitting more complex models Jamie

240 views • 12 slides
Meta-Bayesian Analysis A Bayesian decision-theoretic analysis of Bayesian inference under model

Meta-Bayesian Analysis A Bayesian decision-theoretic analysis of Bayesian inference under model

Meta-Bayesian Analysis A Bayesian decision-theoretic analysis of Bayesian inference under model misspecification Jun Yang joint work with Daniel Roy Department of Statistical Sciences University of Toronto World Congress in Probability and

190 views • 17 slides
Staying Well and Achieving Goals Piper S. Meyer-Kalos, Ph.D. Susan Gingerich, MSW Delbert

Staying Well and Achieving Goals Piper S. Meyer-Kalos, Ph.D. Susan Gingerich, MSW Delbert

Staying Well and Achieving Goals Piper S. Meyer-Kalos, Ph.D. Susan Gingerich, MSW Delbert Robinson, M.D. National Council for Behavioral Health Montefiore Medical Center Northwell Health New York State Office of Mental Health Netsmart

687 views • 25 slides
Graphs and Markov chains Graphs as matrices 0 1 2 3 4 If there is an edge (arrow) from node

Graphs and Markov chains Graphs as matrices 0 1 2 3 4 If there is an edge (arrow) from node

Graphs and Markov chains Graphs as matrices 0 1 2 3 4 If there is an edge (arrow) from node to Adjacency node , then !&quot; = 1 Matrix (otherwise zero) 1 1 0 0 0 1 0 0 0 1 1 1 1 0 0 = 0 0 1 0 0 1

654 views • 30 slides
Designing descriptors Overview of todays lecture Why do we need feature descriptors?

Designing descriptors Overview of todays lecture Why do we need feature descriptors?

Designing descriptors Overview of todays lecture Why do we need feature descriptors? Designing feature descriptors. MOPS descriptor. GIST descriptor. Histogram of Textons descriptor. HOG descriptor. SURF descriptor.

691 views • 55 slides
Patrick Schmidt, Christoph Sterz NUMA-aware SURF Speeded Up Robust Features Object detection

Patrick Schmidt, Christoph Sterz NUMA-aware SURF Speeded Up Robust Features Object detection

Patrick Schmidt, Christoph Sterz NUMA-aware SURF Speeded Up Robust Features Object detection in images. Stitching images. Description of images. 01 [Brnzel et al.] 02 SURF &amp; NUMA satellite images 03 Outline I. SURF

457 views • 34 slides
Towards Robust Natural Language Understanding Group 3 Shengshuo L, Xuhui Z, Zeyu L, Xinyi W,

Towards Robust Natural Language Understanding Group 3 Shengshuo L, Xuhui Z, Zeyu L, Xinyi W,

Towards Robust Natural Language Understanding Group 3 Shengshuo L, Xuhui Z, Zeyu L, Xinyi W, Licor So, why do we need robustness? Goodfellow, I. J., Shlens, J., &amp; Szegedy, C. (2014). Explaining and harnessing adversarial examples.

343 views • 20 slides
On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference Yonatan Belinkov * ,

On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference Yonatan Belinkov * ,

On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference Yonatan Belinkov * , Adam Poliak*, Benjamin Van Durme, Stuart Shieber, Alexander Rush *SEM, Minneapolis, MN June 7, 2019 Co-Authors Yonatan Belinkov Adam Poliak

950 views • 57 slides
Lube : Mitigating Bottlenecks in Hao Wang* Wide Area Data Analytics Baochun Li i Qua Wide Area

Lube : Mitigating Bottlenecks in Hao Wang* Wide Area Data Analytics Baochun Li i Qua Wide Area

HotCloud17 Lube : Mitigating Bottlenecks in Hao Wang* Wide Area Data Analytics Baochun Li i Qua Wide Area Data Analytics DC Master Namenode Workers Datanodes 2 Wide Area Data Analytics Why wide area data analytics? Data Volume

557 views • 19 slides
Moving tables across clusters Scaling a high traffic database Nice to meet you! Developer on

Moving tables across clusters Scaling a high traffic database Nice to meet you! Developer on

Moving tables across clusters Scaling a high traffic database Nice to meet you! Developer on database-services team @ GitHub @bryanaknight on Twitter Tech lead for Women Who Code Boston Spoken at Railsconf and Syntaxcon (2017)

900 views • 51 slides

More recommend