SlideShare a Scribd company logo
MACHINE LEARNING
機械学習
ON THE RIGHT PATH?
正しい道に?
Silicon Brains
www.si-brains.com
Silicon Brains
www.si-brains.com
Machine learning: field of AI that gives computer
systems the ability to "learn" (progressively improve
performance on a specific task) with data, without being
explicitly programmed.
DEFINITION
WHAT IS OUT THERE?
ANN (Artificial Neural Networks): Fixed structure of an
interconnected group of functions with a number of
unknown parameters to be found in order to model
complex, multi-variable functions, find patterns in data or
capture the statistical structure of an unknown
probability function.
NOT MUCH DIFFERENT FROM REGRESSION METHODS
Silicon Brains
www.si-brains.com
WHAT IS THE PROBLEM?
• Current systems do not learn, are “trained” (not much
different than fitting regression coefficients)
• Current systems are static, do not change. Only the
parameters (data) contain the learning
• Current systems are made of arbitrary layers, without
any justification or proof of being optimal
• Current systems use mostly functions that allow an
easy cost function
• Current systems need huge amounts of training data
and time.
Silicon Brains
www.si-brains.com
HOW SHOULD MACHINE LEARNING BE?
• Systems should evolve and change incrementally and
only if they improve with the change
• Learning resides in parameters, functions, nodes and
connections
• Systems can be hierarchically more complex than a
number of layers
• Systems self-optimize continuously
• Learning happens during normal usage
• Learning uses no much more data and effort than
during normal usage
Silicon Brains
www.si-brains.com
WHAT DO SILICON BRAINS PURSUE?
A true Machine Learning system that:
• Learns on the go
• Never stop optimizing itself
• Builds itself based on global optimization
• Contains the minimum or no a priori structure
• Focus is on system self-building, not on problem
solving
Silicon Brains
www.si-brains.com
AND WE BASE OURSELVES ON:
LIFE, the force that has made living beings from plants to
humans along millions of years of evolution
• We learn as we try things, not before
• Life continuously improves (*)
• Life and performance determines success and failure
• Starts from scratch (*)
• Focus is on system self-building, not on problem
solving
(*) Living beings inherit evolution, systems are copied
Silicon Brains
www.si-brains.com
ありがとうございます
Thank you

More Related Content

Similar to Machine learning

Slides-Introduction-to-System-Dynamics-Modeling-October-20-2021.pdf
Slides-Introduction-to-System-Dynamics-Modeling-October-20-2021.pdfSlides-Introduction-to-System-Dynamics-Modeling-October-20-2021.pdf
Slides-Introduction-to-System-Dynamics-Modeling-October-20-2021.pdf
ChristineCheong5
 
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
Egyptian Engineers Association
 
CSA 3702 machine learning module 1
CSA 3702 machine learning module 1CSA 3702 machine learning module 1
CSA 3702 machine learning module 1
Nandhini S
 

Similar to Machine learning (20)

Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
6.12 expert systems
6.12 expert systems6.12 expert systems
6.12 expert systems
 
Machine Learning for AIML course UG.pptx
Machine Learning for AIML course UG.pptxMachine Learning for AIML course UG.pptx
Machine Learning for AIML course UG.pptx
 
ML_Module_1.pdf
ML_Module_1.pdfML_Module_1.pdf
ML_Module_1.pdf
 
E Learning Management System By Tuhin Roy Using PHP
E Learning Management System By Tuhin Roy Using PHPE Learning Management System By Tuhin Roy Using PHP
E Learning Management System By Tuhin Roy Using PHP
 
Slides-Introduction-to-System-Dynamics-Modeling-October-20-2021.pdf
Slides-Introduction-to-System-Dynamics-Modeling-October-20-2021.pdfSlides-Introduction-to-System-Dynamics-Modeling-October-20-2021.pdf
Slides-Introduction-to-System-Dynamics-Modeling-October-20-2021.pdf
 
Webinar Slides - How KeyBank Liberated its IT Ops from Rules-Based Event Mana...
Webinar Slides - How KeyBank Liberated its IT Ops from Rules-Based Event Mana...Webinar Slides - How KeyBank Liberated its IT Ops from Rules-Based Event Mana...
Webinar Slides - How KeyBank Liberated its IT Ops from Rules-Based Event Mana...
 
Andrew NG machine learning
Andrew NG machine learningAndrew NG machine learning
Andrew NG machine learning
 
Applying Systems Thinking to Software Architecture
Applying Systems Thinking to Software ArchitectureApplying Systems Thinking to Software Architecture
Applying Systems Thinking to Software Architecture
 
Intro/Overview on Machine Learning Presentation -2
Intro/Overview on Machine Learning Presentation -2Intro/Overview on Machine Learning Presentation -2
Intro/Overview on Machine Learning Presentation -2
 
Algorithms and Data Structures
Algorithms and Data StructuresAlgorithms and Data Structures
Algorithms and Data Structures
 
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
 
1. everything is a system
1. everything is a system1. everything is a system
1. everything is a system
 
Deep learning summary
Deep learning summaryDeep learning summary
Deep learning summary
 
Simulation of complex systems: the case of crowds (Phd course - lesson 1/7)
Simulation of complex systems: the case of crowds (Phd course - lesson 1/7)Simulation of complex systems: the case of crowds (Phd course - lesson 1/7)
Simulation of complex systems: the case of crowds (Phd course - lesson 1/7)
 
Big data expo - machine learning in the elastic stack
Big data expo - machine learning in the elastic stack Big data expo - machine learning in the elastic stack
Big data expo - machine learning in the elastic stack
 
Vitriol
VitriolVitriol
Vitriol
 
Systems Modeling Overview
Systems Modeling OverviewSystems Modeling Overview
Systems Modeling Overview
 
CSA 3702 machine learning module 1
CSA 3702 machine learning module 1CSA 3702 machine learning module 1
CSA 3702 machine learning module 1
 
Three Tools for "Human-in-the-loop" Data Science
Three Tools for "Human-in-the-loop" Data ScienceThree Tools for "Human-in-the-loop" Data Science
Three Tools for "Human-in-the-loop" Data Science
 

Recently uploaded

Structuring Teams and Portfolios for Success
Structuring Teams and Portfolios for SuccessStructuring Teams and Portfolios for Success
Structuring Teams and Portfolios for Success
UXDXConf
 

Recently uploaded (20)

Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptxUnpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
 
Speed Wins: From Kafka to APIs in Minutes
Speed Wins: From Kafka to APIs in MinutesSpeed Wins: From Kafka to APIs in Minutes
Speed Wins: From Kafka to APIs in Minutes
 
A Business-Centric Approach to Design System Strategy
A Business-Centric Approach to Design System StrategyA Business-Centric Approach to Design System Strategy
A Business-Centric Approach to Design System Strategy
 
SOQL 201 for Admins & Developers: Slice & Dice Your Org’s Data With Aggregate...
SOQL 201 for Admins & Developers: Slice & Dice Your Org’s Data With Aggregate...SOQL 201 for Admins & Developers: Slice & Dice Your Org’s Data With Aggregate...
SOQL 201 for Admins & Developers: Slice & Dice Your Org’s Data With Aggregate...
 
Behind the Scenes From the Manager's Chair: Decoding the Secrets of Successfu...
Behind the Scenes From the Manager's Chair: Decoding the Secrets of Successfu...Behind the Scenes From the Manager's Chair: Decoding the Secrets of Successfu...
Behind the Scenes From the Manager's Chair: Decoding the Secrets of Successfu...
 
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdfSimplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
 
Salesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
Salesforce Adoption – Metrics, Methods, and Motivation, Antone KomSalesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
Salesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
 
UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2
 
Enterprise Knowledge Graphs - Data Summit 2024
Enterprise Knowledge Graphs - Data Summit 2024Enterprise Knowledge Graphs - Data Summit 2024
Enterprise Knowledge Graphs - Data Summit 2024
 
AI presentation and introduction - Retrieval Augmented Generation RAG 101
AI presentation and introduction - Retrieval Augmented Generation RAG 101AI presentation and introduction - Retrieval Augmented Generation RAG 101
AI presentation and introduction - Retrieval Augmented Generation RAG 101
 
Designing for Hardware Accessibility at Comcast
Designing for Hardware Accessibility at ComcastDesigning for Hardware Accessibility at Comcast
Designing for Hardware Accessibility at Comcast
 
AI revolution and Salesforce, Jiří Karpíšek
AI revolution and Salesforce, Jiří KarpíšekAI revolution and Salesforce, Jiří Karpíšek
AI revolution and Salesforce, Jiří Karpíšek
 
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
 
Buy Epson EcoTank L3210 Colour Printer Online.pdf
Buy Epson EcoTank L3210 Colour Printer Online.pdfBuy Epson EcoTank L3210 Colour Printer Online.pdf
Buy Epson EcoTank L3210 Colour Printer Online.pdf
 
Free and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
Free and Effective: Making Flows Publicly Accessible, Yumi IbrahimzadeFree and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
Free and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
 
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya HalderCustom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
 
Structuring Teams and Portfolios for Success
Structuring Teams and Portfolios for SuccessStructuring Teams and Portfolios for Success
Structuring Teams and Portfolios for Success
 
UiPath Test Automation using UiPath Test Suite series, part 1
UiPath Test Automation using UiPath Test Suite series, part 1UiPath Test Automation using UiPath Test Suite series, part 1
UiPath Test Automation using UiPath Test Suite series, part 1
 
IESVE for Early Stage Design and Planning
IESVE for Early Stage Design and PlanningIESVE for Early Stage Design and Planning
IESVE for Early Stage Design and Planning
 
WSO2CONMay2024OpenSourceConferenceDebrief.pptx
WSO2CONMay2024OpenSourceConferenceDebrief.pptxWSO2CONMay2024OpenSourceConferenceDebrief.pptx
WSO2CONMay2024OpenSourceConferenceDebrief.pptx
 

Machine learning

  • 1. MACHINE LEARNING 機械学習 ON THE RIGHT PATH? 正しい道に? Silicon Brains www.si-brains.com
  • 2. Silicon Brains www.si-brains.com Machine learning: field of AI that gives computer systems the ability to "learn" (progressively improve performance on a specific task) with data, without being explicitly programmed. DEFINITION WHAT IS OUT THERE? ANN (Artificial Neural Networks): Fixed structure of an interconnected group of functions with a number of unknown parameters to be found in order to model complex, multi-variable functions, find patterns in data or capture the statistical structure of an unknown probability function. NOT MUCH DIFFERENT FROM REGRESSION METHODS
  • 3. Silicon Brains www.si-brains.com WHAT IS THE PROBLEM? • Current systems do not learn, are “trained” (not much different than fitting regression coefficients) • Current systems are static, do not change. Only the parameters (data) contain the learning • Current systems are made of arbitrary layers, without any justification or proof of being optimal • Current systems use mostly functions that allow an easy cost function • Current systems need huge amounts of training data and time.
  • 4. Silicon Brains www.si-brains.com HOW SHOULD MACHINE LEARNING BE? • Systems should evolve and change incrementally and only if they improve with the change • Learning resides in parameters, functions, nodes and connections • Systems can be hierarchically more complex than a number of layers • Systems self-optimize continuously • Learning happens during normal usage • Learning uses no much more data and effort than during normal usage
  • 5. Silicon Brains www.si-brains.com WHAT DO SILICON BRAINS PURSUE? A true Machine Learning system that: • Learns on the go • Never stop optimizing itself • Builds itself based on global optimization • Contains the minimum or no a priori structure • Focus is on system self-building, not on problem solving
  • 6. Silicon Brains www.si-brains.com AND WE BASE OURSELVES ON: LIFE, the force that has made living beings from plants to humans along millions of years of evolution • We learn as we try things, not before • Life continuously improves (*) • Life and performance determines success and failure • Starts from scratch (*) • Focus is on system self-building, not on problem solving (*) Living beings inherit evolution, systems are copied