SlideShare a Scribd company logo
1 of 21
Bang Xiang Yong
Alexandra Brintrup
Uncertainty Quantification with
Unsupervised Deep learning and Multi-agent system​
Introduction
1. Trend: Machine learning (ML) techniques are a core pillar in Industry 4.0 paradigm
2. Idea: Train a model on a set of data, and predict on unseen data
3. Difference from conventional statistical models:
i. High dimensional data (Heterogeneous sensors)
ii. Complex and non-linear
iii. Dynamic environment (Data is rarely stationary)
4. Example: ZEMA Dataset for Prognosis
i. Given sensors measurements and time of Run-to-Failure of electromechanical cylinders, fit a
model and predict on new machines.
ii. Example of ML pipeline:
Data Stream FFT BFC
Pearson
Correlation
Linear
Discriminant
Analysis
Evaluation
X: Sensors data​
Y: % Degradation
Accuracy (classification)
MSE (regression)
Preprocessing & Model
Challenges
• Q: Can we trust and explain the ML model?
• Problem 1: Lack of uncertainty intervals.
Does the model know what it doesn't know?
• Predictive error is not the same as uncertainty!
• In practice, we want predictions to be 50% +- 3% with “dynamic” uncertainty,
• e.g With a perturbed sensor, we should get 50% +- 10% !
• Problem 2: We have 11 sensors, which sensors are contributing to the model prediction?
• During test, we can only observe the prediction i.e 90% health remaining.
• Why is the model predicting 90%, instead of 30%? Or 60%?
• Which sensors led it to the decisions?
• Problem 3: Limited data availability – ideally we want to have as many run-to failure-examples to
learn from!
• But in practice, we have only very few..
• Testing the trained model on other assets yields unstable performance.
Poor vs Well calibrated uncertainty of classification
Explaining predictions
via contribution of features
Contribution
Development of Hierarchical & Coalitional Bayesian Autoencoders (BAE)
•Unsupervised model. Addressing the lack of faulty data availability.
•Bayesian deep learning. Probabilistic framework – Principled approach towards high
dimensional data with uncertainty bands.
•Explainable AI predictions (XAI): Individual contributions by sensor and features with
uncertainty.
•Multi-agent system. Complex model management and time-series simulation.
Screenshot of agent-
based framework
applying BAE on
sensor network
Addendum: In development - Metrological Agents
Joint work with PTB
• Metrological meta-data class
• Time-series buffer
(Bjoern Ludwig & Max Gruber)
Research Outputs
1. B. X. Yong, T. Pearce and A. Brintrup, "Bayesian Autoencoders: Analysing and Fixing the Bernoulli likelihood for Out-of-Distribution
Detection," 2020. ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning.
2. B. X. Yong, Y. Fathy and A. Brintrup, "Bayesian Autoencoders for Drift Detection in Industrial Environments," 2020 IEEE International
Workshop on Metrology for Industry 4.0 & IoT, Roma, Italy.
3. Bang X. Yong, A. Brintrup. "Multi Agent System for Machine Learning Under Uncertainty in Cyber Physical Manufacturing System". 9th
Workshop on Service Oriented, Holonic and Multi-agent Manufacturing Systems for Industry of the Future
1. agentMET4FOF : Agent-based framework for metrologically-enabled distributed sensor data analytics
• https://github.com/bangxiangyong/agentMET4FOF
2. baetorch : Bayesian autoencoder library
• https://github.com/bangxiangyong/baetorch
Conference papers
Software packages
Work in progress
1. Journal paper on Hierarchical and Coalitional BAE​ for industrial sensors
2. Video tutorials and metrological agents (agentMET4FOF) with PTB
Bayesian Autoencoders as Bayesian Neural Networks
With input X,​ autoencoder (parameterised by theta) reconstructs the input with signal X̂
Training with Bayes Rule:
(unlabelled data)
(reconstructed data)
Prediction:
Mean and variance of log-likelihood of new data x*
(conditioned on training data)
Gaussian Log-Likelihood:
Methods of Sampling from posterior:
• MCMC
• Variational Inference
• Bayesian ensembling
Also known as
reconstruction loss
Intuition - Bayesian Autoencoders as Bayesian Neural Networks
Bayesian ensembling (randomised MAP sampling)
https://github.com/TeaPearce/Bayesian_NN_Ensembles
Epistemic uncertainty:
Bayesian Autoencoders for Out-of-Distribution & Drift Detection
Choice of likelihood matters in detecting out-of-
distribution inputs!
B. X. Yong, Y. Fathy and A. Brintrup, "Bayesian Autoencoders for Drift Detection in Industrial Environments," 2020 IEEE
International Workshop on Metrology for Industry 4.0 & IoT, Roma, Italy.
B. X. Yong, T. Pearce and A. Brintrup, "Bayesian
Autoencoders: Analysing and Fixing the Bernoulli likelihood for Out-of-
Distribution Detection," ICML 2020 Workshop on Uncertainty and
Robustness in Deep Learning.
Ability to distinguish types of drifts (real vs virtual
drifts) on ZEMA hydraulic condition monitoring
dataset
B. X. Yong, Y. Fathy and A. Brintrup, "Bayesian Autoencoders for Drift Detection in
Industrial Environments," 2020 IEEE International Workshop on Metrology for Industry 4.0
& IoT, Roma, Italy.
WIP : Hierarchical & Coalitional BAE
(Experiments on ZEMA EMC Prognosis)
ZEMA EMC Dataset (@zenodo):
i. Assets : 3x run-to-failures
ii. Num cycles (examples)-
6292,6083,5732 cycles
iii. 11 Sensors
iv. Train (10% of initial cycles)
v. Test (90% of remaining cycles)
vi. Each cycle has measurements of -
• 2000 time steps * 11 sensors
• Apply FFT -> 1000 * 11 sensors
https://zenodo.org/record/2702226
WIP: Hierarchical & Coalitional BAE (Configurations)
Vanilla BAE
(1 BAE for 11 sensors)
Coalitional BAE
(1 BAE per sensor)
Single Asset Multi Asset Aggregation
Hierarchical & Coalitional BAE (Axis 3 Lifetime = 6292 cycles)
Vanilla BAE
(1 BAE for 11 sensors)
Coalitional BAE
(1 BAE per sensor)
Single Asset Multi Asset Aggregation
Qualitatively, total log-likelihood gain for
vanilla vs coalitional appears indifferent.
Combining knowledge from other assets, uncertainty
appears higher as condition moves away from healthy
condition (better calibrated?).
Quantitative Comparison
Note: PCC = Pearson Correlation
Intuition: We should expect the LL Gain at Degradation =50% (Half-
life) to be proportional with its overall life time.
• The higher the LL Gain, the healthier it is (vice versa).
WIP: Explainable AI under Uncertainty with BAE
Vanilla BAE
(1 BAE for 11 sensors)
Coalitional BAE
(1 BAE per sensor)
Single Asset Multi Asset Aggregation
Outputs of Vanilla BAE are highly correlated, which may give misleading
explanation in identifying sensor contribution
WIP: Explainable AI under Uncertainty with BAE
• Can we tell which sensor was injected with noise?
Vanilla BAE Coalitional BAE
Contributions
1. Hierarchical & Coalitional Bayesian Autoencoders:
•Bayesian deep learning for unsupervised models.
•Explainable AI predictions (XAI).
•Multi-agent system.
2. Code:
• agentMET4FOF: https://github.com/bangxiangyong/agentMET4FOF
• baetorch: https://github.com/bangxiangyong/baetorch
• MET4FOF repo: https://github.com/Met4FoF
3. Thanks to our collaborators: (open to more!)
• PTB
• NPL
• VSL
•IMBIH​
•ZEMA​
•STRATH
Appendix: Model setup
Vanilla BAE Architecture Coalition BAE Architecture
Each BAE is trained using
automatic learning rate
finder by Leslie Smith for
250 epochs
Appendix:
Appendix:
agentMET4FOF - Connecting Sensors
By: Benedikt Seeger (PTB)
Appendix:
agentMET4FOF – Modularised components
By: Gertjan Kok (VSL)
Appendix:
baetorch – Bayesian Autoencoder library
Features
•Quantify epistemic uncertainty using approximate
Bayesian inference
•MC-Dropout
•Bayesian Ensembling (with Anchored priors)
•Variational Inference (Bayes by Backprop)
•Options for specifying data likelihood p(X|theta) to
Gaussian or Bernoulli
•Quantify (homo/heteroskedestic) aleatoric uncertainty
using Gaussian Likelihood
•Automatic learning rate finder for Bayesian
Autoencoders

More Related Content

What's hot

Logistic Regression | Logistic Regression In Python | Machine Learning Algori...
Logistic Regression | Logistic Regression In Python | Machine Learning Algori...Logistic Regression | Logistic Regression In Python | Machine Learning Algori...
Logistic Regression | Logistic Regression In Python | Machine Learning Algori...Simplilearn
 
Score based generative model
Score based generative modelScore based generative model
Score based generative modelsangyun lee
 
論文紹介:Multimodal Learning with Transformers: A Survey
論文紹介:Multimodal Learning with Transformers: A Survey論文紹介:Multimodal Learning with Transformers: A Survey
論文紹介:Multimodal Learning with Transformers: A SurveyToru Tamaki
 
Tutorial on Deep Generative Models
 Tutorial on Deep Generative Models Tutorial on Deep Generative Models
Tutorial on Deep Generative ModelsMLReview
 
Bayesian Neural Networks
Bayesian Neural NetworksBayesian Neural Networks
Bayesian Neural NetworksNatan Katz
 
研究室内PRML勉強会 8章1節
研究室内PRML勉強会 8章1節研究室内PRML勉強会 8章1節
研究室内PRML勉強会 8章1節Koji Matsuda
 
Dimensionality Reduction
Dimensionality ReductionDimensionality Reduction
Dimensionality ReductionSaad Elbeleidy
 
[DL輪読会]Monaural Audio Source Separationusing Variational Autoencoders
[DL輪読会]Monaural Audio Source Separationusing Variational Autoencoders[DL輪読会]Monaural Audio Source Separationusing Variational Autoencoders
[DL輪読会]Monaural Audio Source Separationusing Variational AutoencodersDeep Learning JP
 
[DL輪読会]Estimating Predictive Uncertainty via Prior Networks
[DL輪読会]Estimating Predictive Uncertainty via Prior Networks[DL輪読会]Estimating Predictive Uncertainty via Prior Networks
[DL輪読会]Estimating Predictive Uncertainty via Prior NetworksDeep Learning JP
 
【論文読み会】Pyraformer_Low-Complexity Pyramidal Attention for Long-Range Time Seri...
【論文読み会】Pyraformer_Low-Complexity Pyramidal Attention for Long-Range Time Seri...【論文読み会】Pyraformer_Low-Complexity Pyramidal Attention for Long-Range Time Seri...
【論文読み会】Pyraformer_Low-Complexity Pyramidal Attention for Long-Range Time Seri...ARISE analytics
 
An Introduction to Supervised Machine Learning and Pattern Classification: Th...
An Introduction to Supervised Machine Learning and Pattern Classification: Th...An Introduction to Supervised Machine Learning and Pattern Classification: Th...
An Introduction to Supervised Machine Learning and Pattern Classification: Th...Sebastian Raschka
 
Explicit Density Models
Explicit Density ModelsExplicit Density Models
Explicit Density ModelsSangwoo Mo
 
Res netと派生研究の紹介
Res netと派生研究の紹介Res netと派生研究の紹介
Res netと派生研究の紹介masataka nishimori
 
Deep Learning Hardware: Past, Present, & Future
Deep Learning Hardware: Past, Present, & FutureDeep Learning Hardware: Past, Present, & Future
Deep Learning Hardware: Past, Present, & FutureRouyun Pan
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningOswald Campesato
 
Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...
Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...
Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...Preferred Networks
 
Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Appsilon Data Science
 
Causal discovery and prediction mechanisms
Causal discovery and prediction mechanismsCausal discovery and prediction mechanisms
Causal discovery and prediction mechanismsShiga University, RIKEN
 
ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]Dongmin Choi
 

What's hot (20)

Logistic Regression | Logistic Regression In Python | Machine Learning Algori...
Logistic Regression | Logistic Regression In Python | Machine Learning Algori...Logistic Regression | Logistic Regression In Python | Machine Learning Algori...
Logistic Regression | Logistic Regression In Python | Machine Learning Algori...
 
Score based generative model
Score based generative modelScore based generative model
Score based generative model
 
論文紹介:Multimodal Learning with Transformers: A Survey
論文紹介:Multimodal Learning with Transformers: A Survey論文紹介:Multimodal Learning with Transformers: A Survey
論文紹介:Multimodal Learning with Transformers: A Survey
 
Tutorial on Deep Generative Models
 Tutorial on Deep Generative Models Tutorial on Deep Generative Models
Tutorial on Deep Generative Models
 
Bayesian Neural Networks
Bayesian Neural NetworksBayesian Neural Networks
Bayesian Neural Networks
 
研究室内PRML勉強会 8章1節
研究室内PRML勉強会 8章1節研究室内PRML勉強会 8章1節
研究室内PRML勉強会 8章1節
 
Dimensionality Reduction
Dimensionality ReductionDimensionality Reduction
Dimensionality Reduction
 
[DL輪読会]Monaural Audio Source Separationusing Variational Autoencoders
[DL輪読会]Monaural Audio Source Separationusing Variational Autoencoders[DL輪読会]Monaural Audio Source Separationusing Variational Autoencoders
[DL輪読会]Monaural Audio Source Separationusing Variational Autoencoders
 
[DL輪読会]Estimating Predictive Uncertainty via Prior Networks
[DL輪読会]Estimating Predictive Uncertainty via Prior Networks[DL輪読会]Estimating Predictive Uncertainty via Prior Networks
[DL輪読会]Estimating Predictive Uncertainty via Prior Networks
 
【論文読み会】Pyraformer_Low-Complexity Pyramidal Attention for Long-Range Time Seri...
【論文読み会】Pyraformer_Low-Complexity Pyramidal Attention for Long-Range Time Seri...【論文読み会】Pyraformer_Low-Complexity Pyramidal Attention for Long-Range Time Seri...
【論文読み会】Pyraformer_Low-Complexity Pyramidal Attention for Long-Range Time Seri...
 
An Introduction to Supervised Machine Learning and Pattern Classification: Th...
An Introduction to Supervised Machine Learning and Pattern Classification: Th...An Introduction to Supervised Machine Learning and Pattern Classification: Th...
An Introduction to Supervised Machine Learning and Pattern Classification: Th...
 
Explicit Density Models
Explicit Density ModelsExplicit Density Models
Explicit Density Models
 
Res netと派生研究の紹介
Res netと派生研究の紹介Res netと派生研究の紹介
Res netと派生研究の紹介
 
Learning from imbalanced data
Learning from imbalanced data Learning from imbalanced data
Learning from imbalanced data
 
Deep Learning Hardware: Past, Present, & Future
Deep Learning Hardware: Past, Present, & FutureDeep Learning Hardware: Past, Present, & Future
Deep Learning Hardware: Past, Present, & Future
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...
Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...
Introduction to Graph Neural Networks: Basics and Applications - Katsuhiko Is...
 
Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)
 
Causal discovery and prediction mechanisms
Causal discovery and prediction mechanismsCausal discovery and prediction mechanisms
Causal discovery and prediction mechanisms
 
ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]ViT (Vision Transformer) Review [CDM]
ViT (Vision Transformer) Review [CDM]
 

Similar to Uncertainty Quantification with Unsupervised Deep learning and Multi Agent System

PPT - Deep and Confident Prediction For Time Series at Uber
PPT - Deep and Confident Prediction For Time Series at UberPPT - Deep and Confident Prediction For Time Series at Uber
PPT - Deep and Confident Prediction For Time Series at UberJisang Yoon
 
Bayesian Autoencoders for anomaly detection in industrial environments
Bayesian Autoencoders for anomaly detection in industrial environmentsBayesian Autoencoders for anomaly detection in industrial environments
Bayesian Autoencoders for anomaly detection in industrial environmentsBang Xiang Yong
 
Neural networks, naïve bayes and decision tree machine learning
Neural networks, naïve bayes and decision tree machine learningNeural networks, naïve bayes and decision tree machine learning
Neural networks, naïve bayes and decision tree machine learningFrancisco E. Figueroa-Nigaglioni
 
Advances in Bayesian Learning
Advances in Bayesian LearningAdvances in Bayesian Learning
Advances in Bayesian Learningbutest
 
IEEE Fuzzy system Title and Abstract 2016
IEEE Fuzzy system Title and Abstract 2016 IEEE Fuzzy system Title and Abstract 2016
IEEE Fuzzy system Title and Abstract 2016 tsysglobalsolutions
 
Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...
Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...
Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...Quantopian
 
Knowledge Science for AI-based biomedical and clinical applications
Knowledge Science for AI-based biomedical and clinical applicationsKnowledge Science for AI-based biomedical and clinical applications
Knowledge Science for AI-based biomedical and clinical applicationsCatia Pesquita
 
Multibiometric Secure Index Value Code Generation for Authentication and Retr...
Multibiometric Secure Index Value Code Generation for Authentication and Retr...Multibiometric Secure Index Value Code Generation for Authentication and Retr...
Multibiometric Secure Index Value Code Generation for Authentication and Retr...ijsrd.com
 
ISMB2014読み会 イントロ + Deep learning of the tissue-regulated splicing code
ISMB2014読み会 イントロ + Deep learning of the tissue-regulated splicing codeISMB2014読み会 イントロ + Deep learning of the tissue-regulated splicing code
ISMB2014読み会 イントロ + Deep learning of the tissue-regulated splicing codeKengo Sato
 
Deep learning: Cutting through the Myths and Hype
Deep learning: Cutting through the Myths and HypeDeep learning: Cutting through the Myths and Hype
Deep learning: Cutting through the Myths and HypeSiby Jose Plathottam
 
Paper sharing_deep learning for smart manufacturing methods and applications
Paper sharing_deep learning for smart manufacturing methods and applicationsPaper sharing_deep learning for smart manufacturing methods and applications
Paper sharing_deep learning for smart manufacturing methods and applicationsYOU SHENG CHEN
 
Interpretability and informatics of deep learning in medical images3
Interpretability and informatics of deep learning in medical images3Interpretability and informatics of deep learning in medical images3
Interpretability and informatics of deep learning in medical images3Namkug Kim
 
Rsqrd AI - ML Interpretability: Beyond Feature Importance
Rsqrd AI - ML Interpretability: Beyond Feature ImportanceRsqrd AI - ML Interpretability: Beyond Feature Importance
Rsqrd AI - ML Interpretability: Beyond Feature ImportanceAlessya Visnjic
 
Multivariate data analysis and visualization tools for biological data
Multivariate data analysis and visualization tools for biological dataMultivariate data analysis and visualization tools for biological data
Multivariate data analysis and visualization tools for biological dataDmitry Grapov
 
Introduction to Deep Learning and some Neuroimaging Applications
Introduction to Deep Learning and some Neuroimaging ApplicationsIntroduction to Deep Learning and some Neuroimaging Applications
Introduction to Deep Learning and some Neuroimaging ApplicationsWalter Hugo Lopez Pinaya
 
self operating maps
self operating mapsself operating maps
self operating mapsAltafSMT
 
A Study on Comparison of Bayesian Network Structure Learning Algorithms for S...
A Study on Comparison of Bayesian Network Structure Learning Algorithms for S...A Study on Comparison of Bayesian Network Structure Learning Algorithms for S...
A Study on Comparison of Bayesian Network Structure Learning Algorithms for S...Jae-seong Yoo
 
20090219 The case for another systems biology modelling environment
20090219 The case for another systems biology modelling environment20090219 The case for another systems biology modelling environment
20090219 The case for another systems biology modelling environmentJonathan Blakes
 
Why Neurons have thousands of synapses? A model of sequence memory in the brain
Why Neurons have thousands of synapses? A model of sequence memory in the brainWhy Neurons have thousands of synapses? A model of sequence memory in the brain
Why Neurons have thousands of synapses? A model of sequence memory in the brainNumenta
 

Similar to Uncertainty Quantification with Unsupervised Deep learning and Multi Agent System (20)

PPT - Deep and Confident Prediction For Time Series at Uber
PPT - Deep and Confident Prediction For Time Series at UberPPT - Deep and Confident Prediction For Time Series at Uber
PPT - Deep and Confident Prediction For Time Series at Uber
 
Bayesian Autoencoders for anomaly detection in industrial environments
Bayesian Autoencoders for anomaly detection in industrial environmentsBayesian Autoencoders for anomaly detection in industrial environments
Bayesian Autoencoders for anomaly detection in industrial environments
 
NRNB EAC Report 2011
NRNB EAC Report 2011NRNB EAC Report 2011
NRNB EAC Report 2011
 
Neural networks, naïve bayes and decision tree machine learning
Neural networks, naïve bayes and decision tree machine learningNeural networks, naïve bayes and decision tree machine learning
Neural networks, naïve bayes and decision tree machine learning
 
Advances in Bayesian Learning
Advances in Bayesian LearningAdvances in Bayesian Learning
Advances in Bayesian Learning
 
IEEE Fuzzy system Title and Abstract 2016
IEEE Fuzzy system Title and Abstract 2016 IEEE Fuzzy system Title and Abstract 2016
IEEE Fuzzy system Title and Abstract 2016
 
Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...
Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...
Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...
 
Knowledge Science for AI-based biomedical and clinical applications
Knowledge Science for AI-based biomedical and clinical applicationsKnowledge Science for AI-based biomedical and clinical applications
Knowledge Science for AI-based biomedical and clinical applications
 
Multibiometric Secure Index Value Code Generation for Authentication and Retr...
Multibiometric Secure Index Value Code Generation for Authentication and Retr...Multibiometric Secure Index Value Code Generation for Authentication and Retr...
Multibiometric Secure Index Value Code Generation for Authentication and Retr...
 
ISMB2014読み会 イントロ + Deep learning of the tissue-regulated splicing code
ISMB2014読み会 イントロ + Deep learning of the tissue-regulated splicing codeISMB2014読み会 イントロ + Deep learning of the tissue-regulated splicing code
ISMB2014読み会 イントロ + Deep learning of the tissue-regulated splicing code
 
Deep learning: Cutting through the Myths and Hype
Deep learning: Cutting through the Myths and HypeDeep learning: Cutting through the Myths and Hype
Deep learning: Cutting through the Myths and Hype
 
Paper sharing_deep learning for smart manufacturing methods and applications
Paper sharing_deep learning for smart manufacturing methods and applicationsPaper sharing_deep learning for smart manufacturing methods and applications
Paper sharing_deep learning for smart manufacturing methods and applications
 
Interpretability and informatics of deep learning in medical images3
Interpretability and informatics of deep learning in medical images3Interpretability and informatics of deep learning in medical images3
Interpretability and informatics of deep learning in medical images3
 
Rsqrd AI - ML Interpretability: Beyond Feature Importance
Rsqrd AI - ML Interpretability: Beyond Feature ImportanceRsqrd AI - ML Interpretability: Beyond Feature Importance
Rsqrd AI - ML Interpretability: Beyond Feature Importance
 
Multivariate data analysis and visualization tools for biological data
Multivariate data analysis and visualization tools for biological dataMultivariate data analysis and visualization tools for biological data
Multivariate data analysis and visualization tools for biological data
 
Introduction to Deep Learning and some Neuroimaging Applications
Introduction to Deep Learning and some Neuroimaging ApplicationsIntroduction to Deep Learning and some Neuroimaging Applications
Introduction to Deep Learning and some Neuroimaging Applications
 
self operating maps
self operating mapsself operating maps
self operating maps
 
A Study on Comparison of Bayesian Network Structure Learning Algorithms for S...
A Study on Comparison of Bayesian Network Structure Learning Algorithms for S...A Study on Comparison of Bayesian Network Structure Learning Algorithms for S...
A Study on Comparison of Bayesian Network Structure Learning Algorithms for S...
 
20090219 The case for another systems biology modelling environment
20090219 The case for another systems biology modelling environment20090219 The case for another systems biology modelling environment
20090219 The case for another systems biology modelling environment
 
Why Neurons have thousands of synapses? A model of sequence memory in the brain
Why Neurons have thousands of synapses? A model of sequence memory in the brainWhy Neurons have thousands of synapses? A model of sequence memory in the brain
Why Neurons have thousands of synapses? A model of sequence memory in the brain
 

More from Bang Xiang Yong

Bayesian Autoencoders (BAE) & Honest Thoughts on research
Bayesian Autoencoders (BAE) & Honest Thoughts on research Bayesian Autoencoders (BAE) & Honest Thoughts on research
Bayesian Autoencoders (BAE) & Honest Thoughts on research Bang Xiang Yong
 
Proposal for Linking Concept Drift and uncertainty of Machine learning
Proposal for Linking Concept Drift and uncertainty of Machine learningProposal for Linking Concept Drift and uncertainty of Machine learning
Proposal for Linking Concept Drift and uncertainty of Machine learningBang Xiang Yong
 
PhD First Year Conference (MAY 2019)
PhD First Year Conference (MAY 2019)PhD First Year Conference (MAY 2019)
PhD First Year Conference (MAY 2019)Bang Xiang Yong
 
First Year Report, PhD presentation
First Year Report, PhD presentationFirst Year Report, PhD presentation
First Year Report, PhD presentationBang Xiang Yong
 
SOHOMA19 Conference slides
SOHOMA19 Conference slidesSOHOMA19 Conference slides
SOHOMA19 Conference slidesBang Xiang Yong
 
Use cases - agentMET4FOF
Use cases - agentMET4FOFUse cases - agentMET4FOF
Use cases - agentMET4FOFBang Xiang Yong
 

More from Bang Xiang Yong (7)

Bayesian Autoencoders (BAE) & Honest Thoughts on research
Bayesian Autoencoders (BAE) & Honest Thoughts on research Bayesian Autoencoders (BAE) & Honest Thoughts on research
Bayesian Autoencoders (BAE) & Honest Thoughts on research
 
Proposal for Linking Concept Drift and uncertainty of Machine learning
Proposal for Linking Concept Drift and uncertainty of Machine learningProposal for Linking Concept Drift and uncertainty of Machine learning
Proposal for Linking Concept Drift and uncertainty of Machine learning
 
PhD First Year Conference (MAY 2019)
PhD First Year Conference (MAY 2019)PhD First Year Conference (MAY 2019)
PhD First Year Conference (MAY 2019)
 
First Year Report, PhD presentation
First Year Report, PhD presentationFirst Year Report, PhD presentation
First Year Report, PhD presentation
 
SOHOMA19 Conference slides
SOHOMA19 Conference slidesSOHOMA19 Conference slides
SOHOMA19 Conference slides
 
Use cases - agentMET4FOF
Use cases - agentMET4FOFUse cases - agentMET4FOF
Use cases - agentMET4FOF
 
Espriex 2017 slides
Espriex 2017 slidesEspriex 2017 slides
Espriex 2017 slides
 

Recently uploaded

B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxStephen266013
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
Data Warehouse , Data Cube Computation
Data Warehouse   , Data Cube ComputationData Warehouse   , Data Cube Computation
Data Warehouse , Data Cube Computationsit20ad004
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptxAnupama Kate
 
Data Science Jobs and Salaries Analysis.pptx
Data Science Jobs and Salaries Analysis.pptxData Science Jobs and Salaries Analysis.pptx
Data Science Jobs and Salaries Analysis.pptxFurkanTasci3
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxEmmanuel Dauda
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfLars Albertsson
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfLars Albertsson
 
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfKantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfSocial Samosa
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...Pooja Nehwal
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPramod Kumar Srivastava
 
VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...
VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...
VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...Suhani Kapoor
 
Unveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystUnveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystSamantha Rae Coolbeth
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfRachmat Ramadhan H
 
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service BhilaiLow Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service BhilaiSuhani Kapoor
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsappssapnasaifi408
 

Recently uploaded (20)

Russian Call Girls Dwarka Sector 15 💓 Delhi 9999965857 @Sabina Modi VVIP MODE...
Russian Call Girls Dwarka Sector 15 💓 Delhi 9999965857 @Sabina Modi VVIP MODE...Russian Call Girls Dwarka Sector 15 💓 Delhi 9999965857 @Sabina Modi VVIP MODE...
Russian Call Girls Dwarka Sector 15 💓 Delhi 9999965857 @Sabina Modi VVIP MODE...
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docx
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
Data Warehouse , Data Cube Computation
Data Warehouse   , Data Cube ComputationData Warehouse   , Data Cube Computation
Data Warehouse , Data Cube Computation
 
E-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptxE-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptx
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
Data Science Jobs and Salaries Analysis.pptx
Data Science Jobs and Salaries Analysis.pptxData Science Jobs and Salaries Analysis.pptx
Data Science Jobs and Salaries Analysis.pptx
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptx
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdf
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdf
 
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfKantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
 
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
 
VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...
VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...
VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...
 
Unveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystUnveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data Analyst
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
 
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service BhilaiLow Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
 

Uncertainty Quantification with Unsupervised Deep learning and Multi Agent System

  • 1. Bang Xiang Yong Alexandra Brintrup Uncertainty Quantification with Unsupervised Deep learning and Multi-agent system​
  • 2. Introduction 1. Trend: Machine learning (ML) techniques are a core pillar in Industry 4.0 paradigm 2. Idea: Train a model on a set of data, and predict on unseen data 3. Difference from conventional statistical models: i. High dimensional data (Heterogeneous sensors) ii. Complex and non-linear iii. Dynamic environment (Data is rarely stationary) 4. Example: ZEMA Dataset for Prognosis i. Given sensors measurements and time of Run-to-Failure of electromechanical cylinders, fit a model and predict on new machines. ii. Example of ML pipeline: Data Stream FFT BFC Pearson Correlation Linear Discriminant Analysis Evaluation X: Sensors data​ Y: % Degradation Accuracy (classification) MSE (regression) Preprocessing & Model
  • 3. Challenges • Q: Can we trust and explain the ML model? • Problem 1: Lack of uncertainty intervals. Does the model know what it doesn't know? • Predictive error is not the same as uncertainty! • In practice, we want predictions to be 50% +- 3% with “dynamic” uncertainty, • e.g With a perturbed sensor, we should get 50% +- 10% ! • Problem 2: We have 11 sensors, which sensors are contributing to the model prediction? • During test, we can only observe the prediction i.e 90% health remaining. • Why is the model predicting 90%, instead of 30%? Or 60%? • Which sensors led it to the decisions? • Problem 3: Limited data availability – ideally we want to have as many run-to failure-examples to learn from! • But in practice, we have only very few.. • Testing the trained model on other assets yields unstable performance. Poor vs Well calibrated uncertainty of classification Explaining predictions via contribution of features
  • 4. Contribution Development of Hierarchical & Coalitional Bayesian Autoencoders (BAE) •Unsupervised model. Addressing the lack of faulty data availability. •Bayesian deep learning. Probabilistic framework – Principled approach towards high dimensional data with uncertainty bands. •Explainable AI predictions (XAI): Individual contributions by sensor and features with uncertainty. •Multi-agent system. Complex model management and time-series simulation. Screenshot of agent- based framework applying BAE on sensor network
  • 5. Addendum: In development - Metrological Agents Joint work with PTB • Metrological meta-data class • Time-series buffer (Bjoern Ludwig & Max Gruber)
  • 6. Research Outputs 1. B. X. Yong, T. Pearce and A. Brintrup, "Bayesian Autoencoders: Analysing and Fixing the Bernoulli likelihood for Out-of-Distribution Detection," 2020. ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning. 2. B. X. Yong, Y. Fathy and A. Brintrup, "Bayesian Autoencoders for Drift Detection in Industrial Environments," 2020 IEEE International Workshop on Metrology for Industry 4.0 & IoT, Roma, Italy. 3. Bang X. Yong, A. Brintrup. "Multi Agent System for Machine Learning Under Uncertainty in Cyber Physical Manufacturing System". 9th Workshop on Service Oriented, Holonic and Multi-agent Manufacturing Systems for Industry of the Future 1. agentMET4FOF : Agent-based framework for metrologically-enabled distributed sensor data analytics • https://github.com/bangxiangyong/agentMET4FOF 2. baetorch : Bayesian autoencoder library • https://github.com/bangxiangyong/baetorch Conference papers Software packages Work in progress 1. Journal paper on Hierarchical and Coalitional BAE​ for industrial sensors 2. Video tutorials and metrological agents (agentMET4FOF) with PTB
  • 7. Bayesian Autoencoders as Bayesian Neural Networks With input X,​ autoencoder (parameterised by theta) reconstructs the input with signal X̂ Training with Bayes Rule: (unlabelled data) (reconstructed data) Prediction: Mean and variance of log-likelihood of new data x* (conditioned on training data) Gaussian Log-Likelihood: Methods of Sampling from posterior: • MCMC • Variational Inference • Bayesian ensembling Also known as reconstruction loss
  • 8. Intuition - Bayesian Autoencoders as Bayesian Neural Networks Bayesian ensembling (randomised MAP sampling) https://github.com/TeaPearce/Bayesian_NN_Ensembles Epistemic uncertainty:
  • 9. Bayesian Autoencoders for Out-of-Distribution & Drift Detection Choice of likelihood matters in detecting out-of- distribution inputs! B. X. Yong, Y. Fathy and A. Brintrup, "Bayesian Autoencoders for Drift Detection in Industrial Environments," 2020 IEEE International Workshop on Metrology for Industry 4.0 & IoT, Roma, Italy. B. X. Yong, T. Pearce and A. Brintrup, "Bayesian Autoencoders: Analysing and Fixing the Bernoulli likelihood for Out-of- Distribution Detection," ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning. Ability to distinguish types of drifts (real vs virtual drifts) on ZEMA hydraulic condition monitoring dataset B. X. Yong, Y. Fathy and A. Brintrup, "Bayesian Autoencoders for Drift Detection in Industrial Environments," 2020 IEEE International Workshop on Metrology for Industry 4.0 & IoT, Roma, Italy.
  • 10. WIP : Hierarchical & Coalitional BAE (Experiments on ZEMA EMC Prognosis) ZEMA EMC Dataset (@zenodo): i. Assets : 3x run-to-failures ii. Num cycles (examples)- 6292,6083,5732 cycles iii. 11 Sensors iv. Train (10% of initial cycles) v. Test (90% of remaining cycles) vi. Each cycle has measurements of - • 2000 time steps * 11 sensors • Apply FFT -> 1000 * 11 sensors https://zenodo.org/record/2702226
  • 11. WIP: Hierarchical & Coalitional BAE (Configurations) Vanilla BAE (1 BAE for 11 sensors) Coalitional BAE (1 BAE per sensor) Single Asset Multi Asset Aggregation
  • 12. Hierarchical & Coalitional BAE (Axis 3 Lifetime = 6292 cycles) Vanilla BAE (1 BAE for 11 sensors) Coalitional BAE (1 BAE per sensor) Single Asset Multi Asset Aggregation Qualitatively, total log-likelihood gain for vanilla vs coalitional appears indifferent. Combining knowledge from other assets, uncertainty appears higher as condition moves away from healthy condition (better calibrated?).
  • 13. Quantitative Comparison Note: PCC = Pearson Correlation Intuition: We should expect the LL Gain at Degradation =50% (Half- life) to be proportional with its overall life time. • The higher the LL Gain, the healthier it is (vice versa).
  • 14. WIP: Explainable AI under Uncertainty with BAE Vanilla BAE (1 BAE for 11 sensors) Coalitional BAE (1 BAE per sensor) Single Asset Multi Asset Aggregation Outputs of Vanilla BAE are highly correlated, which may give misleading explanation in identifying sensor contribution
  • 15. WIP: Explainable AI under Uncertainty with BAE • Can we tell which sensor was injected with noise? Vanilla BAE Coalitional BAE
  • 16. Contributions 1. Hierarchical & Coalitional Bayesian Autoencoders: •Bayesian deep learning for unsupervised models. •Explainable AI predictions (XAI). •Multi-agent system. 2. Code: • agentMET4FOF: https://github.com/bangxiangyong/agentMET4FOF • baetorch: https://github.com/bangxiangyong/baetorch • MET4FOF repo: https://github.com/Met4FoF 3. Thanks to our collaborators: (open to more!) • PTB • NPL • VSL •IMBIH​ •ZEMA​ •STRATH
  • 17. Appendix: Model setup Vanilla BAE Architecture Coalition BAE Architecture Each BAE is trained using automatic learning rate finder by Leslie Smith for 250 epochs
  • 19. Appendix: agentMET4FOF - Connecting Sensors By: Benedikt Seeger (PTB)
  • 20. Appendix: agentMET4FOF – Modularised components By: Gertjan Kok (VSL)
  • 21. Appendix: baetorch – Bayesian Autoencoder library Features •Quantify epistemic uncertainty using approximate Bayesian inference •MC-Dropout •Bayesian Ensembling (with Anchored priors) •Variational Inference (Bayes by Backprop) •Options for specifying data likelihood p(X|theta) to Gaussian or Bernoulli •Quantify (homo/heteroskedestic) aleatoric uncertainty using Gaussian Likelihood •Automatic learning rate finder for Bayesian Autoencoders