SlideShare una empresa de Scribd logo
1 de 50
Descargar para leer sin conexión
03/04/2019 Bertrand Thirion 1
Statistical inference in
high-dimension & application to
brain imaging
Imaging and machine learning workshop
Bertrand Thirion,
bertrand.thirion@inria.fr
03/04/2019 Bertrand Thirion 2
Cognitive neuroscience
How are cognitive activities affected or controlled
by neural circuits in the brain ?
03/04/2019 Bertrand Thirion 3
The brain, the mind and the
scanner
Cognitive theories
Brain
Scanner
FMRI data
Brain
mapping
Experimental
paradigm
stimuli
03/04/2019 Bertrand Thirion 4
The brain, the mind and the
scanner
Cognitive theories
Brain
Scanner
FMRI data
Decoding
Encoding
Brain
mapping
Experimental
paradigm
stimuli
03/04/2019 Bertrand Thirion 5
Encoding: mapping cognitive
functions to brain activity
right hand-
left hand
listen-read
Button press -
reading
Computation -
instructions
expression
- intention
Guess the
gender
Face
trustworthiness
false belief –
mechanistic
(auditory) False belief –
mechanistic
(visual)
Grasping-
orientation
judgement
Hand – side
judgement
Intention -
random
Sentence -
checkerboards
saccades -
fixation
Speech-non
speech
03/04/2019 Bertrand Thirion 6
Resolution increases
2007:
3 mm
2014:
1.5 mm
2021:
0.5 mm ?
p = 50,000 p = 400,000 p = 107
03/04/2019 Bertrand Thirion 7
better estimators for large-scale
brain imaging
●
A causal framework for brain activity decoding
●
Dimension reduction for images
●
Fast regularized ensembles of models
●
Statistical inference for high-dimensional models
03/04/2019 Bertrand Thirion 8
Causal reasoning on
encoding/decoding
Task Brain activity Behavior
Causal encoding models
P(X|T)
Causal decoding models
P(B|X)
Anti-causal decoding models
P(T|X)
Anti-causal encoding models
P(X|B)
[Weichwald et al Nimg 2015]
03/04/2019 Bertrand Thirion 9
Causal interpretation
Encoding: causal
Decoding: anti-causalTask
X1
X2
Xp
...
X1
X2
Xp
... Behavior
Encoding: anti-causal
Decoding: causal
03/04/2019 Bertrand Thirion 10
Causal reasoning on
encoding/decoding
[Weichwald et al. NIMG 2015]
Task
X1
X2
Xp
...
03/04/2019 Bertrand Thirion 11
Causal reasoning on
encoding/decoding
[Weichwald et al. NIMG 2015]
Task
X1
X2
Xp
...
03/04/2019 Bertrand Thirion 12
Causal reasoning on
encoding/decoding
[Weichwald et al. NIMG 2015]
03/04/2019 Bertrand Thirion 13
Causal reasoning on
encoding/decoding
[Weichwald et al. NIMG 2015]
03/04/2019 Bertrand Thirion 14
Joint encoding and decoding
[Schwartz et al. NIPS 2013, Varoquaux et al. PCB 2018]
“Encoding” “Decoding”
03/04/2019 Bertrand Thirion 15
Decoding
maps
03/04/2019 Bertrand Thirion 16
Joint encoding and decoding
[Schwartz et al. NIPS 2013, Varoquaux et al. PCB 2018]
03/04/2019 Bertrand Thirion 17
Statistical associations and
causal reasoning
●
Problems:
– Establish non-independence based on finite
datasets → statistical tests
– Large number of conditioning variables
– Encoding models: Multiple comparison issues
– Decoding problem: statistical tests in multiple
regression
03/04/2019 Bertrand Thirion 18
Brain activity decoding
X1
X2
Xp
... y
●
behavior = f (brain activity)
w
03/04/2019 Bertrand Thirion 19
Outline
●
A causal framework for brain activity decoding
●
Dimension reduction for images
●
Fast regularized ensembles of Models
●
Statistical inference for high-dimensional
models
03/04/2019 Bertrand Thirion 20
Compression in the image
domain
●
Reduce the complexity of learning algorithms:
p→k ≪ p
●
Random projections = fast generic solution, but
– Sub-optimal for structured signals
– Not invertible when p and k are large
●
Local redundancy → feature grouping
strategies / clustering: “super-pixels”
– Fast clustering procedures needed (large-k regime)
03/04/2019 Bertrand Thirion 21
Superpixels as an image operator
03/04/2019 Bertrand Thirion 22
Crafting good image compression
●
Key assumption: signal of interest L-Lipschitz
●
Feature grouping matrix
●
almost trivially:
●
Worst case
Need a fast method to learn balanced clusters
03/04/2019 Bertrand Thirion 23
Denoising properties
●
Noisy signal model
●
Denoising
●
Equal-size clusters
03/04/2019 Bertrand Thirion 24
Recursive neighbor Agglomeration
Based on local decisions = fast (linear time) – avoid percolation
[Thirion et al. Stamlins 2015, Hoyos Idrobo PAMI 2018]
ReNA
03/04/2019 Bertrand Thirion 25
Effect on data analysis tasks
Impressive speed-up and increased accuracy with
respect to non-compressed representation
– Clustering has a denoising effect
[Hoyos Idrobo IEEE PAMI 2018]
03/04/2019 Bertrand Thirion 26
Outline
●
A causal framework for brain activity decoding
●
Dimension reduction for images
●
Fast regularized ensembles of Models
●
Statistical inference for high-dimensional
models
03/04/2019 Bertrand Thirion 27
Bagging of clustered models
X
Clustering
(create
contiguous
regions)
y
Solve
regression
on cluster-
based
representation
average
...
various
clusterings
03/04/2019 Bertrand Thirion 28
Computationally efficient structure
State of the art
solution: not
very stable, but
cheap
“fast regularized ensembles of models”
03/04/2019 Bertrand Thirion 29
Computationally efficient structure
03/04/2019 Bertrand Thirion 30
Effect on prediction accuracy
“fast regularized
ensembles of models”
[Hoyos Idrobo et al PRNI 2015,
Neuroimage 2017, PAMI 2018]
03/04/2019 Bertrand Thirion 31
More results
[Hoyos Idrobo et al PRNI 2015, Neuroimage 2017, PAMI 2018]
03/04/2019 Bertrand Thirion 32
Outline
●
A causal framework for brain activity decoding
●
Dimension reduction for images
●
Fast regularized ensembles of Models
●
Statistical inference for high-dimensional
models
03/04/2019 Bertrand Thirion 33
Statistical inference on w
●
Standard solutions for high-dimensional linear
models (p ≅ n)
– Corrected ridge [Bühlmann 2013]
– Desparsified Lasso [Zhang & Zhang 2014, Montanari 2014]
– Multi-split [Meinshausen 2009], knockoffs [Candès 2015+]
●
Fail for p ≫ n
● Inference: find {j: wj > 0} with some statistical
guarantees
03/04/2019 Bertrand Thirion 34
Desparsified Lasso
[Zhang & Zhang 2014 Series B Stat Meth]
03/04/2019 Bertrand Thirion 35
Desparsified Lasso
03/04/2019 Bertrand Thirion 36
Preliminary assessment
03/04/2019 Bertrand Thirion 37
Large p → need dimension reduction
Large p kills statistical power CDL tames variance
p=2000, n=100
[Chevalier et al. subm. To MICCAI]
03/04/2019 Bertrand Thirion 38
Adaptation to brain imaging
Step 1: compression by clustering
Step 2: inference on compressed representations
Step 3: ensembling iterate with different parcellations
→ aggregate p-values (see also FReM)
Clustered
Desparsified
Lasso
Ensemble of
Clustered
Desparsified
Lasso
03/04/2019 Bertrand Thirion 39
From CDL to ECDL
DL p-values
from different
clusterings
aggregation
03/04/2019 Bertrand Thirion 40
ECDL for brain imaging
03/04/2019 Bertrand Thirion 41
δ-error control
03/04/2019 Bertrand Thirion 42
δ-error control
03/04/2019 Bertrand Thirion 43
δ-FWER control
03/04/2019 Bertrand Thirion 44
δ-FWER-control
03/04/2019 Bertrand Thirion 45
Simulations: ECDL > CDL
[Chevalier et al. MICCAI 2018]
03/04/2019 Bertrand Thirion 46
Experiments: PR and FWER control
Better PR with ECDL + More accurate FWER control
[Chevalier et al. MICCAI 2018]
03/04/2019 Bertrand Thirion 47
Effects on real data
[Nguyen et al. IPMI 2019, Chevalier et al. MICCAI 2018]
Social cognition
Visual feature discrimination
Language vs maths
HCP dataset, n=900
03/04/2019 Bertrand Thirion 48
Conclusion
●
Causal reasoning →
conditional association analysis
●
Large-p data bring challenges:
– Computation cost
– Difficulty of statistical inference
●
Solutions: ensembling,
subsampling, compression
●
Efficient stochastic regularizers
●
Ongoing comparison with
knockoff
WIP
●
Classification setting
●
Use of bootstrap
[Nguyen et al. IPMI 2019] [Aydore et al. subm]
03/04/2019 Bertrand Thirion 49
From good ideas to good practices:
software
●
Machine learning in Python
●
Machine learning for neuroimaging
http://nilearn.github.io
●
BSD, Python, OSS
– Classification of (neuroimaging) data
– Network analysis
03/04/2019 Bertrand Thirion 50
Acknowledgements
Parietal
G. Varoquaux,
A. Gramfort,
P. Ciuciu,
D. Wassermann,
D. Engemann,
B. Nguyen
A.L. Grilo Pinho,
E. Dohmatob,
A. Mensch,
J.A. Chevalier,
A. Hoyos idrobo,
D. Bzdok,
J. Dockès,
P. Cerda,
C. Lazarus
D. La Rocca
G. Lemaitre
L. El Gueddari
O. Grisel
M. Massias
P. Ablin
H. Janati
J. Massich
K. Dadi
H. Richard
C. Petitot
Other collaborators
R. Poldrack,
J. Haxby
C. F. Gorgolevski
J. Salmon
S. Arlot
M. Lerasle

Más contenido relacionado

Similar a Statistical inference in high-dimension & application to brain imaging

BIM Data Mining Unit3 by Tekendra Nath Yogi
 BIM Data Mining Unit3 by Tekendra Nath Yogi BIM Data Mining Unit3 by Tekendra Nath Yogi
BIM Data Mining Unit3 by Tekendra Nath YogiTekendra Nath Yogi
 
What Does Responsible Data Science Mean?
What Does Responsible Data Science Mean?What Does Responsible Data Science Mean?
What Does Responsible Data Science Mean?Philip Bourne
 
BigMLSchool: Customer Segmentation
BigMLSchool: Customer SegmentationBigMLSchool: Customer Segmentation
BigMLSchool: Customer SegmentationBigML, Inc
 
Deep Learning with Databricks
Deep Learning with Databricks  Deep Learning with Databricks
Deep Learning with Databricks Henning Kropp
 
An empirical investigation on big data analytics (BDA) and innovation perform...
An empirical investigation on big data analytics (BDA) and innovation perform...An empirical investigation on big data analytics (BDA) and innovation perform...
An empirical investigation on big data analytics (BDA) and innovation perform...Ahad Zare Ravasan
 
School project
School projectSchool project
School projectCHISANHONG
 
National Seminar on Data Analytics
National Seminar on Data AnalyticsNational Seminar on Data Analytics
National Seminar on Data AnalyticsRajaKrishnan M
 
CARE 2019 - Challenging the Integration of Personal Assistant Agents and Cogn...
CARE 2019 - Challenging the Integration of Personal Assistant Agents and Cogn...CARE 2019 - Challenging the Integration of Personal Assistant Agents and Cogn...
CARE 2019 - Challenging the Integration of Personal Assistant Agents and Cogn...Michael Bosello
 
FACE RECOGNITION USING NEURAL NETWORK
FACE RECOGNITION USING NEURAL NETWORKFACE RECOGNITION USING NEURAL NETWORK
FACE RECOGNITION USING NEURAL NETWORKTITHI DAN
 
Use of Hough Transform and Homography for the Creation of Image Corpora for S...
Use of Hough Transform and Homography for the Creation of Image Corpora for S...Use of Hough Transform and Homography for the Creation of Image Corpora for S...
Use of Hough Transform and Homography for the Creation of Image Corpora for S...IJCI JOURNAL
 
Mental Model for Exploratory Data Analysis Applications for Structured Proble...
Mental Model for Exploratory Data Analysis Applications for Structured Proble...Mental Model for Exploratory Data Analysis Applications for Structured Proble...
Mental Model for Exploratory Data Analysis Applications for Structured Proble...Jukka-Matti Turtiainen
 
Statistical Data Analysis | Data Analysis | Statistics Services | Data Collec...
Statistical Data Analysis | Data Analysis | Statistics Services | Data Collec...Statistical Data Analysis | Data Analysis | Statistics Services | Data Collec...
Statistical Data Analysis | Data Analysis | Statistics Services | Data Collec...Stats Statswork
 
Practical Challenges ML Workflows
Practical Challenges ML WorkflowsPractical Challenges ML Workflows
Practical Challenges ML WorkflowsJenny Midwinter
 
Literature survey andrei_manta_0
Literature survey andrei_manta_0Literature survey andrei_manta_0
Literature survey andrei_manta_0darshanahiren
 
Sydney WiMLDS Meetup 25 November 2019 -Technical Presentation
Sydney WiMLDS Meetup 25 November 2019 -Technical PresentationSydney WiMLDS Meetup 25 November 2019 -Technical Presentation
Sydney WiMLDS Meetup 25 November 2019 -Technical PresentationWendy Wong
 
IT Trends : skills for tech pros of tomorrow
IT Trends : skills for tech pros of tomorrowIT Trends : skills for tech pros of tomorrow
IT Trends : skills for tech pros of tomorrowCHARLES Frédéric
 
Data science landscape in the insurance industry
Data science landscape in the insurance industryData science landscape in the insurance industry
Data science landscape in the insurance industryStefano Perfetti
 
Multitask Adversarial Learning of Deep Neural Networks for Medical Imaging an...
Multitask Adversarial Learning of Deep Neural Networks for Medical Imaging an...Multitask Adversarial Learning of Deep Neural Networks for Medical Imaging an...
Multitask Adversarial Learning of Deep Neural Networks for Medical Imaging an...Debdoot Sheet
 
Incremental rebalancing learning on evolving data streams
Incremental rebalancing learning on evolving data streamsIncremental rebalancing learning on evolving data streams
Incremental rebalancing learning on evolving data streamsAlessio Bernardo
 
______BS-Math_-Math-80-Number-Theory.docx
______BS-Math_-Math-80-Number-Theory.docx______BS-Math_-Math-80-Number-Theory.docx
______BS-Math_-Math-80-Number-Theory.docxOphelElainePanabang
 

Similar a Statistical inference in high-dimension & application to brain imaging (20)

BIM Data Mining Unit3 by Tekendra Nath Yogi
 BIM Data Mining Unit3 by Tekendra Nath Yogi BIM Data Mining Unit3 by Tekendra Nath Yogi
BIM Data Mining Unit3 by Tekendra Nath Yogi
 
What Does Responsible Data Science Mean?
What Does Responsible Data Science Mean?What Does Responsible Data Science Mean?
What Does Responsible Data Science Mean?
 
BigMLSchool: Customer Segmentation
BigMLSchool: Customer SegmentationBigMLSchool: Customer Segmentation
BigMLSchool: Customer Segmentation
 
Deep Learning with Databricks
Deep Learning with Databricks  Deep Learning with Databricks
Deep Learning with Databricks
 
An empirical investigation on big data analytics (BDA) and innovation perform...
An empirical investigation on big data analytics (BDA) and innovation perform...An empirical investigation on big data analytics (BDA) and innovation perform...
An empirical investigation on big data analytics (BDA) and innovation perform...
 
School project
School projectSchool project
School project
 
National Seminar on Data Analytics
National Seminar on Data AnalyticsNational Seminar on Data Analytics
National Seminar on Data Analytics
 
CARE 2019 - Challenging the Integration of Personal Assistant Agents and Cogn...
CARE 2019 - Challenging the Integration of Personal Assistant Agents and Cogn...CARE 2019 - Challenging the Integration of Personal Assistant Agents and Cogn...
CARE 2019 - Challenging the Integration of Personal Assistant Agents and Cogn...
 
FACE RECOGNITION USING NEURAL NETWORK
FACE RECOGNITION USING NEURAL NETWORKFACE RECOGNITION USING NEURAL NETWORK
FACE RECOGNITION USING NEURAL NETWORK
 
Use of Hough Transform and Homography for the Creation of Image Corpora for S...
Use of Hough Transform and Homography for the Creation of Image Corpora for S...Use of Hough Transform and Homography for the Creation of Image Corpora for S...
Use of Hough Transform and Homography for the Creation of Image Corpora for S...
 
Mental Model for Exploratory Data Analysis Applications for Structured Proble...
Mental Model for Exploratory Data Analysis Applications for Structured Proble...Mental Model for Exploratory Data Analysis Applications for Structured Proble...
Mental Model for Exploratory Data Analysis Applications for Structured Proble...
 
Statistical Data Analysis | Data Analysis | Statistics Services | Data Collec...
Statistical Data Analysis | Data Analysis | Statistics Services | Data Collec...Statistical Data Analysis | Data Analysis | Statistics Services | Data Collec...
Statistical Data Analysis | Data Analysis | Statistics Services | Data Collec...
 
Practical Challenges ML Workflows
Practical Challenges ML WorkflowsPractical Challenges ML Workflows
Practical Challenges ML Workflows
 
Literature survey andrei_manta_0
Literature survey andrei_manta_0Literature survey andrei_manta_0
Literature survey andrei_manta_0
 
Sydney WiMLDS Meetup 25 November 2019 -Technical Presentation
Sydney WiMLDS Meetup 25 November 2019 -Technical PresentationSydney WiMLDS Meetup 25 November 2019 -Technical Presentation
Sydney WiMLDS Meetup 25 November 2019 -Technical Presentation
 
IT Trends : skills for tech pros of tomorrow
IT Trends : skills for tech pros of tomorrowIT Trends : skills for tech pros of tomorrow
IT Trends : skills for tech pros of tomorrow
 
Data science landscape in the insurance industry
Data science landscape in the insurance industryData science landscape in the insurance industry
Data science landscape in the insurance industry
 
Multitask Adversarial Learning of Deep Neural Networks for Medical Imaging an...
Multitask Adversarial Learning of Deep Neural Networks for Medical Imaging an...Multitask Adversarial Learning of Deep Neural Networks for Medical Imaging an...
Multitask Adversarial Learning of Deep Neural Networks for Medical Imaging an...
 
Incremental rebalancing learning on evolving data streams
Incremental rebalancing learning on evolving data streamsIncremental rebalancing learning on evolving data streams
Incremental rebalancing learning on evolving data streams
 
______BS-Math_-Math-80-Number-Theory.docx
______BS-Math_-Math-80-Number-Theory.docx______BS-Math_-Math-80-Number-Theory.docx
______BS-Math_-Math-80-Number-Theory.docx
 

Último

MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdflior mazor
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...apidays
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodJuan lago vázquez
 

Último (20)

MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 

Statistical inference in high-dimension & application to brain imaging

  • 1. 03/04/2019 Bertrand Thirion 1 Statistical inference in high-dimension & application to brain imaging Imaging and machine learning workshop Bertrand Thirion, bertrand.thirion@inria.fr
  • 2. 03/04/2019 Bertrand Thirion 2 Cognitive neuroscience How are cognitive activities affected or controlled by neural circuits in the brain ?
  • 3. 03/04/2019 Bertrand Thirion 3 The brain, the mind and the scanner Cognitive theories Brain Scanner FMRI data Brain mapping Experimental paradigm stimuli
  • 4. 03/04/2019 Bertrand Thirion 4 The brain, the mind and the scanner Cognitive theories Brain Scanner FMRI data Decoding Encoding Brain mapping Experimental paradigm stimuli
  • 5. 03/04/2019 Bertrand Thirion 5 Encoding: mapping cognitive functions to brain activity right hand- left hand listen-read Button press - reading Computation - instructions expression - intention Guess the gender Face trustworthiness false belief – mechanistic (auditory) False belief – mechanistic (visual) Grasping- orientation judgement Hand – side judgement Intention - random Sentence - checkerboards saccades - fixation Speech-non speech
  • 6. 03/04/2019 Bertrand Thirion 6 Resolution increases 2007: 3 mm 2014: 1.5 mm 2021: 0.5 mm ? p = 50,000 p = 400,000 p = 107
  • 7. 03/04/2019 Bertrand Thirion 7 better estimators for large-scale brain imaging ● A causal framework for brain activity decoding ● Dimension reduction for images ● Fast regularized ensembles of models ● Statistical inference for high-dimensional models
  • 8. 03/04/2019 Bertrand Thirion 8 Causal reasoning on encoding/decoding Task Brain activity Behavior Causal encoding models P(X|T) Causal decoding models P(B|X) Anti-causal decoding models P(T|X) Anti-causal encoding models P(X|B) [Weichwald et al Nimg 2015]
  • 9. 03/04/2019 Bertrand Thirion 9 Causal interpretation Encoding: causal Decoding: anti-causalTask X1 X2 Xp ... X1 X2 Xp ... Behavior Encoding: anti-causal Decoding: causal
  • 10. 03/04/2019 Bertrand Thirion 10 Causal reasoning on encoding/decoding [Weichwald et al. NIMG 2015] Task X1 X2 Xp ...
  • 11. 03/04/2019 Bertrand Thirion 11 Causal reasoning on encoding/decoding [Weichwald et al. NIMG 2015] Task X1 X2 Xp ...
  • 12. 03/04/2019 Bertrand Thirion 12 Causal reasoning on encoding/decoding [Weichwald et al. NIMG 2015]
  • 13. 03/04/2019 Bertrand Thirion 13 Causal reasoning on encoding/decoding [Weichwald et al. NIMG 2015]
  • 14. 03/04/2019 Bertrand Thirion 14 Joint encoding and decoding [Schwartz et al. NIPS 2013, Varoquaux et al. PCB 2018] “Encoding” “Decoding”
  • 15. 03/04/2019 Bertrand Thirion 15 Decoding maps
  • 16. 03/04/2019 Bertrand Thirion 16 Joint encoding and decoding [Schwartz et al. NIPS 2013, Varoquaux et al. PCB 2018]
  • 17. 03/04/2019 Bertrand Thirion 17 Statistical associations and causal reasoning ● Problems: – Establish non-independence based on finite datasets → statistical tests – Large number of conditioning variables – Encoding models: Multiple comparison issues – Decoding problem: statistical tests in multiple regression
  • 18. 03/04/2019 Bertrand Thirion 18 Brain activity decoding X1 X2 Xp ... y ● behavior = f (brain activity) w
  • 19. 03/04/2019 Bertrand Thirion 19 Outline ● A causal framework for brain activity decoding ● Dimension reduction for images ● Fast regularized ensembles of Models ● Statistical inference for high-dimensional models
  • 20. 03/04/2019 Bertrand Thirion 20 Compression in the image domain ● Reduce the complexity of learning algorithms: p→k ≪ p ● Random projections = fast generic solution, but – Sub-optimal for structured signals – Not invertible when p and k are large ● Local redundancy → feature grouping strategies / clustering: “super-pixels” – Fast clustering procedures needed (large-k regime)
  • 21. 03/04/2019 Bertrand Thirion 21 Superpixels as an image operator
  • 22. 03/04/2019 Bertrand Thirion 22 Crafting good image compression ● Key assumption: signal of interest L-Lipschitz ● Feature grouping matrix ● almost trivially: ● Worst case Need a fast method to learn balanced clusters
  • 23. 03/04/2019 Bertrand Thirion 23 Denoising properties ● Noisy signal model ● Denoising ● Equal-size clusters
  • 24. 03/04/2019 Bertrand Thirion 24 Recursive neighbor Agglomeration Based on local decisions = fast (linear time) – avoid percolation [Thirion et al. Stamlins 2015, Hoyos Idrobo PAMI 2018] ReNA
  • 25. 03/04/2019 Bertrand Thirion 25 Effect on data analysis tasks Impressive speed-up and increased accuracy with respect to non-compressed representation – Clustering has a denoising effect [Hoyos Idrobo IEEE PAMI 2018]
  • 26. 03/04/2019 Bertrand Thirion 26 Outline ● A causal framework for brain activity decoding ● Dimension reduction for images ● Fast regularized ensembles of Models ● Statistical inference for high-dimensional models
  • 27. 03/04/2019 Bertrand Thirion 27 Bagging of clustered models X Clustering (create contiguous regions) y Solve regression on cluster- based representation average ... various clusterings
  • 28. 03/04/2019 Bertrand Thirion 28 Computationally efficient structure State of the art solution: not very stable, but cheap “fast regularized ensembles of models”
  • 29. 03/04/2019 Bertrand Thirion 29 Computationally efficient structure
  • 30. 03/04/2019 Bertrand Thirion 30 Effect on prediction accuracy “fast regularized ensembles of models” [Hoyos Idrobo et al PRNI 2015, Neuroimage 2017, PAMI 2018]
  • 31. 03/04/2019 Bertrand Thirion 31 More results [Hoyos Idrobo et al PRNI 2015, Neuroimage 2017, PAMI 2018]
  • 32. 03/04/2019 Bertrand Thirion 32 Outline ● A causal framework for brain activity decoding ● Dimension reduction for images ● Fast regularized ensembles of Models ● Statistical inference for high-dimensional models
  • 33. 03/04/2019 Bertrand Thirion 33 Statistical inference on w ● Standard solutions for high-dimensional linear models (p ≅ n) – Corrected ridge [Bühlmann 2013] – Desparsified Lasso [Zhang & Zhang 2014, Montanari 2014] – Multi-split [Meinshausen 2009], knockoffs [Candès 2015+] ● Fail for p ≫ n ● Inference: find {j: wj > 0} with some statistical guarantees
  • 34. 03/04/2019 Bertrand Thirion 34 Desparsified Lasso [Zhang & Zhang 2014 Series B Stat Meth]
  • 35. 03/04/2019 Bertrand Thirion 35 Desparsified Lasso
  • 36. 03/04/2019 Bertrand Thirion 36 Preliminary assessment
  • 37. 03/04/2019 Bertrand Thirion 37 Large p → need dimension reduction Large p kills statistical power CDL tames variance p=2000, n=100 [Chevalier et al. subm. To MICCAI]
  • 38. 03/04/2019 Bertrand Thirion 38 Adaptation to brain imaging Step 1: compression by clustering Step 2: inference on compressed representations Step 3: ensembling iterate with different parcellations → aggregate p-values (see also FReM) Clustered Desparsified Lasso Ensemble of Clustered Desparsified Lasso
  • 39. 03/04/2019 Bertrand Thirion 39 From CDL to ECDL DL p-values from different clusterings aggregation
  • 40. 03/04/2019 Bertrand Thirion 40 ECDL for brain imaging
  • 41. 03/04/2019 Bertrand Thirion 41 δ-error control
  • 42. 03/04/2019 Bertrand Thirion 42 δ-error control
  • 43. 03/04/2019 Bertrand Thirion 43 δ-FWER control
  • 44. 03/04/2019 Bertrand Thirion 44 δ-FWER-control
  • 45. 03/04/2019 Bertrand Thirion 45 Simulations: ECDL > CDL [Chevalier et al. MICCAI 2018]
  • 46. 03/04/2019 Bertrand Thirion 46 Experiments: PR and FWER control Better PR with ECDL + More accurate FWER control [Chevalier et al. MICCAI 2018]
  • 47. 03/04/2019 Bertrand Thirion 47 Effects on real data [Nguyen et al. IPMI 2019, Chevalier et al. MICCAI 2018] Social cognition Visual feature discrimination Language vs maths HCP dataset, n=900
  • 48. 03/04/2019 Bertrand Thirion 48 Conclusion ● Causal reasoning → conditional association analysis ● Large-p data bring challenges: – Computation cost – Difficulty of statistical inference ● Solutions: ensembling, subsampling, compression ● Efficient stochastic regularizers ● Ongoing comparison with knockoff WIP ● Classification setting ● Use of bootstrap [Nguyen et al. IPMI 2019] [Aydore et al. subm]
  • 49. 03/04/2019 Bertrand Thirion 49 From good ideas to good practices: software ● Machine learning in Python ● Machine learning for neuroimaging http://nilearn.github.io ● BSD, Python, OSS – Classification of (neuroimaging) data – Network analysis
  • 50. 03/04/2019 Bertrand Thirion 50 Acknowledgements Parietal G. Varoquaux, A. Gramfort, P. Ciuciu, D. Wassermann, D. Engemann, B. Nguyen A.L. Grilo Pinho, E. Dohmatob, A. Mensch, J.A. Chevalier, A. Hoyos idrobo, D. Bzdok, J. Dockès, P. Cerda, C. Lazarus D. La Rocca G. Lemaitre L. El Gueddari O. Grisel M. Massias P. Ablin H. Janati J. Massich K. Dadi H. Richard C. Petitot Other collaborators R. Poldrack, J. Haxby C. F. Gorgolevski J. Salmon S. Arlot M. Lerasle