SlideShare uma empresa Scribd logo
1 de 14
Baixar para ler offline
Guaranteeing Deep Neural Network
Outputs in a Feasible Region
Hiroshi Maruyama
PFN Fellow
2
What is “invariance” in ML?
3
Fundamental Limitation of Machine Learning :
It’s Statistics!
Original Distribution
i. i. d.
Training Data Set
Trained Model
Random
Sampling !!
No guarantee of “100% correctness”
4
In deep learning, any point in the Rn is possible as output
Input
Output:A Point in Rn
For any point P in Rn, there is a combination of
the input, training data set, hyper-parameters,
and random-number seed that generates P
• Training Data Set
• Hyper parameters
• Random # seeds
• … and program itself
5
Example: Controlling a Drone
DL ModuleSensor Input
Reference Point
How to Guarantee that the reference point is always in the region?
6
Definition: Feasible Region and Non-Feasible Solutions
Feasible Region
Non-feasible
solutions
We assume the feasible region is convex
DNN
Policy
Filter
Simple Solution: Policy Filter
Remove (no output) Snap to the boarder
Proposed Solution: Transformation of Output Space
Rn → Rn Space
Transformation
Select an interior point (called pivot)
Step 1 (Bounding) : Transform Rn to n-dimensional
hypercube
9
Sigmoid Function
Apply Sigmoid on each dimension
Move the pivot to the origin of the hypercube
Step 2: Shrink / Extend every point towards the origin
10
11
Step 3: Finally move the pivot to the original position
For any combination of the input, training data set, hyper parameters, and
random number seed, the output is guarantted to be feasible
Proposed transformation works for any “star-shaped” space
12
Make this x0 the pivot
Set S is Star-shaped iff there is x0 s.t. for any interior point x,
the line segment xx0 ∈ S
Teacher signals can be given in the transformed space
Original DNN
(parameters to be
trained)
Transformation to
Feasible Region
(fixed parameters)
Back propagation
Rn Space
Input
Feasible Region
Teacher
Signal
loss
14
Thank You
Twitter: @maruyama

Mais conteúdo relacionado

Semelhante a 20181204i mlse 1

기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법
기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법
기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법
NAVER Engineering
 
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
台灣資料科學年會
 

Semelhante a 20181204i mlse 1 (13)

convolutional_rbm.ppt
convolutional_rbm.pptconvolutional_rbm.ppt
convolutional_rbm.ppt
 
Distributed deep learning_over_spark_20_nov_2014_ver_2.8
Distributed deep learning_over_spark_20_nov_2014_ver_2.8Distributed deep learning_over_spark_20_nov_2014_ver_2.8
Distributed deep learning_over_spark_20_nov_2014_ver_2.8
 
기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법
기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법
기계학습을 이용하여 정적 분석기의 안전성을 선별적으로 조절하는 방법
 
V2.0 open power ai virtual university deep learning and ai introduction
V2.0 open power ai virtual university   deep learning and ai introductionV2.0 open power ai virtual university   deep learning and ai introduction
V2.0 open power ai virtual university deep learning and ai introduction
 
Deep Learning Introduction - WeCloudData
Deep Learning Introduction - WeCloudDataDeep Learning Introduction - WeCloudData
Deep Learning Introduction - WeCloudData
 
VOICE CONTROLLED WHEELCHAIR using Amharic.pdf
VOICE CONTROLLED WHEELCHAIR using Amharic.pdfVOICE CONTROLLED WHEELCHAIR using Amharic.pdf
VOICE CONTROLLED WHEELCHAIR using Amharic.pdf
 
Muhammad Usman Akhtar | Ph.D Scholar | Wuhan University | School of Co...
Muhammad Usman Akhtar  |  Ph.D Scholar  |  Wuhan  University  |  School of Co...Muhammad Usman Akhtar  |  Ph.D Scholar  |  Wuhan  University  |  School of Co...
Muhammad Usman Akhtar | Ph.D Scholar | Wuhan University | School of Co...
 
Compiler Design- Machine Independent Optimizations
Compiler Design- Machine Independent OptimizationsCompiler Design- Machine Independent Optimizations
Compiler Design- Machine Independent Optimizations
 
NLP Classifier Models & Metrics
NLP Classifier Models & MetricsNLP Classifier Models & Metrics
NLP Classifier Models & Metrics
 
AI and Deep Learning
AI and Deep Learning AI and Deep Learning
AI and Deep Learning
 
Introduction to deep learning @ Startup.ML by Andres Rodriguez
Introduction to deep learning @ Startup.ML by Andres RodriguezIntroduction to deep learning @ Startup.ML by Andres Rodriguez
Introduction to deep learning @ Startup.ML by Andres Rodriguez
 
Thesis Presentation
Thesis PresentationThesis Presentation
Thesis Presentation
 
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
 

Mais de Hiroshi Maruyama

Mais de Hiroshi Maruyama (16)

20230925プレジデント社60周年.pdf
20230925プレジデント社60周年.pdf20230925プレジデント社60周年.pdf
20230925プレジデント社60周年.pdf
 
20230912JSSST大会基調講演_丸山.pdf
20230912JSSST大会基調講演_丸山.pdf20230912JSSST大会基調講演_丸山.pdf
20230912JSSST大会基調講演_丸山.pdf
 
20230712Kuramae-Seminar.pdf
20230712Kuramae-Seminar.pdf20230712Kuramae-Seminar.pdf
20230712Kuramae-Seminar.pdf
 
202212APSEC.pptx.pdf
202212APSEC.pptx.pdf202212APSEC.pptx.pdf
202212APSEC.pptx.pdf
 
20210731知財学会研究会
20210731知財学会研究会20210731知財学会研究会
20210731知財学会研究会
 
2021 06-17 ism-symposium
2021 06-17 ism-symposium2021 06-17 ism-symposium
2021 06-17 ism-symposium
 
Jsai
JsaiJsai
Jsai
 
20181212 ibm aot
20181212 ibm aot20181212 ibm aot
20181212 ibm aot
 
20181205 sakigake
20181205 sakigake20181205 sakigake
20181205 sakigake
 
20181204i mlse discussions
20181204i mlse discussions20181204i mlse discussions
20181204i mlse discussions
 
20181120 ldp ai
20181120 ldp ai20181120 ldp ai
20181120 ldp ai
 
20181030 fun
20181030 fun20181030 fun
20181030 fun
 
20180719 cocn dist
20180719 cocn dist20180719 cocn dist
20180719 cocn dist
 
20180601 ai discussions
20180601 ai discussions20180601 ai discussions
20180601 ai discussions
 
構造改革徹底推進会合におけるプレゼン
構造改革徹底推進会合におけるプレゼン構造改革徹底推進会合におけるプレゼン
構造改革徹底推進会合におけるプレゼン
 
深層学習よもやま話
深層学習よもやま話深層学習よもやま話
深層学習よもやま話
 

Último

CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
giselly40
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
Enterprise Knowledge
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
Earley Information Science
 

Último (20)

Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
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
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
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
 
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
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
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
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
Evaluating the top large language models.pdf
Evaluating the top large language models.pdfEvaluating the top large language models.pdf
Evaluating the top large language models.pdf
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
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...
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 

20181204i mlse 1

  • 1. Guaranteeing Deep Neural Network Outputs in a Feasible Region Hiroshi Maruyama PFN Fellow
  • 3. 3 Fundamental Limitation of Machine Learning : It’s Statistics! Original Distribution i. i. d. Training Data Set Trained Model Random Sampling !! No guarantee of “100% correctness”
  • 4. 4 In deep learning, any point in the Rn is possible as output Input Output:A Point in Rn For any point P in Rn, there is a combination of the input, training data set, hyper-parameters, and random-number seed that generates P • Training Data Set • Hyper parameters • Random # seeds • … and program itself
  • 5. 5 Example: Controlling a Drone DL ModuleSensor Input Reference Point How to Guarantee that the reference point is always in the region?
  • 6. 6 Definition: Feasible Region and Non-Feasible Solutions Feasible Region Non-feasible solutions We assume the feasible region is convex
  • 7. DNN Policy Filter Simple Solution: Policy Filter Remove (no output) Snap to the boarder
  • 8. Proposed Solution: Transformation of Output Space Rn → Rn Space Transformation Select an interior point (called pivot)
  • 9. Step 1 (Bounding) : Transform Rn to n-dimensional hypercube 9 Sigmoid Function Apply Sigmoid on each dimension Move the pivot to the origin of the hypercube
  • 10. Step 2: Shrink / Extend every point towards the origin 10
  • 11. 11 Step 3: Finally move the pivot to the original position For any combination of the input, training data set, hyper parameters, and random number seed, the output is guarantted to be feasible
  • 12. Proposed transformation works for any “star-shaped” space 12 Make this x0 the pivot Set S is Star-shaped iff there is x0 s.t. for any interior point x, the line segment xx0 ∈ S
  • 13. Teacher signals can be given in the transformed space Original DNN (parameters to be trained) Transformation to Feasible Region (fixed parameters) Back propagation Rn Space Input Feasible Region Teacher Signal loss