SlideShare a Scribd company logo
1 of 10
DEEP LEARNING
ITP810 : KEY TECHNOLOGIES FOR 4TH INDUSTRIAL REVOLUTION, PROF. JONGHEUNG PARK
PREPARED BY : RIRI KUSUMARANI / 20155636
REPORT CONTENT
 Concept of Deep Learning
 How Deep Learning Works
 Architectures
 ImageNet Competition
 Application of Deep Learning
 Reinforcement Learning
DEEP LEARNING
 Deep learning is strongly related in machine learning in
which it shows us an upward trend since early 2005
 There are at least 4 people who are also known as the big
four in Deep Learning area. These people are : Geoffrey
Hinton, Yan LeCunn,Andrew Ng and Yosua Bengio.
 The basic idea about deep learning is the availability of
computational power which allow machines to recognize
objects and translate speech in real time. If we relate this
with previous topic in ITP810, it means deep learning also
allows artificial intelligence to get smarter each day.
Figure 1 : Trends on Deep Learning & The Big Four
Source : ITP810 Class Materials
How Deep Learning Works?
 Programmers would train a neural network to
detect an object or phoneme by blitzing the
network with digitized versions of images
containing those objects or sound waves
containing those phonemes.
 If the network didn’t accurately recognize a
particular pattern, an algorithm would adjust the
weights.
 The eventual goal of this training was to get the
network to consistently recognize the patterns in
speech or sets of images that we humans know
say, the phoneme “d” or the image of a dog.
Figure 2 : Machine Learning Workflow
Source : ITP810 Class Materials
DEEP LEARNING ARCHITECTURES
 There are many well-known deep learning architectures. Some of these are Convolutional Neural
Network , Recurrent Neural Network and Deep Belief Network.
 Convolutional Neural Network might be the most famous architecture amongst all and it’s simple to
understand. CNN mostly being used for image processing..
IMAGENET COMPETITION
 ImageNet is an image dataset organized according to the WordNet hierarchy.
ImageNet aim to provide on average 1000 images to illustrate each synset. Images
of each concept are quality-controlled and human-annotated. ImageNet aims to
offer tens of millions of cleanly sorted images for most of the concepts in the
WordNet hierarchy.
 In accordance with this, ImageNet starts a competition which is done each year
since 2010. This competition is also known as ImageNet Large Scale Visual
Recognition Challenge (ILSVRC).
 The idea of this competition is to allow researchers to compare progress in
detection across a wider variety of objects - taking advantage of the quite
expensive labeling effort. Another motivation is to measure the progress of
computer vision for large scale image indexing for retrieval and annotation.
Figure 3 : Exampel of ImageNet Competition
Source : Imagenet.net
APPLICATION OF DEEP LEARNING
 Deep learning allows the application of it to many aspects in daily life.
 For example, by using CNN Architecture, machine can detect the movement of human through video, image
captioning, visual question answering, semantic segmentation and automatic colorization of black and white
images.
REINFORCEMENT LEARNING
What?
 Reinforcement Learning is another branch of machine
learning in which it doesn’t rely on examples of correct
behavior, goal oriented , maximize a reward signal and
there’s existence of trade-off between exploration and
exploitation.
 The picture on the right summarizes the difference
between reinforcement learning with other branches of
machine learning such as supervised learning and
unsupervised learning.
How Reinforcement Learning Works?
 There will be at least three main factors in RL:
Environment, agent , reward and policy. The main
goal for RL is to maximize reward.
Figure 4 &5 : How RL Works
Source : ITP810 Class Materials
ALPHA-GO
 If we discuss about artificial intelligence and deep learning, we can’t avoid the recent topic of AlphaGo
which happens to be the renowned Deep Learning application.
 Prof.Lee spent last hour of his lecture to discuss the logic of AlphaGo which I found very much
interesting and relatable with the topic that we’ve been discussing for the last 2 weeks.
 During his class, he explain in a way that students who don’t have basic knowledge on deep learning,
understand how AlphaGo operates.
 The concept of reducing search space is said to be the main feauture and strength of AlphaGo . Even this
reduce space sounds simple, the technical requirement behind is complicated.
 AlphaGo itself is exposed to millions of games and board position.

More Related Content

What's hot

Deep Learning in real world @Deep Learning Tokyo
Deep Learning in real world @Deep Learning TokyoDeep Learning in real world @Deep Learning Tokyo
Deep Learning in real world @Deep Learning TokyoPreferred Networks
 
introduction to machin learning
introduction to machin learningintroduction to machin learning
introduction to machin learningnilimapatel6
 
What is Deep Learning?
What is Deep Learning?What is Deep Learning?
What is Deep Learning?NVIDIA
 
True Artificial Intelligence Will Change Everything
True Artificial Intelligence Will Change Everything True Artificial Intelligence Will Change Everything
True Artificial Intelligence Will Change Everything Russia.AI
 
A quick peek into the word of AI
A quick peek into the word of AIA quick peek into the word of AI
A quick peek into the word of AISubhendu Dey
 
Machine Learning
Machine LearningMachine Learning
Machine Learningbutest
 
Demystifying Ml, DL and AI
Demystifying Ml, DL and AIDemystifying Ml, DL and AI
Demystifying Ml, DL and AIGreg Werner
 
Fundamentals of Artificial Intelligence — QU AIO Leadership in AI
Fundamentals of Artificial Intelligence — QU AIO Leadership in AIFundamentals of Artificial Intelligence — QU AIO Leadership in AI
Fundamentals of Artificial Intelligence — QU AIO Leadership in AIJunaid Qadir
 
Ajit Jaokar, Data Science for IoT professor at Oxford University “Enterprise ...
Ajit Jaokar, Data Science for IoT professor at Oxford University “Enterprise ...Ajit Jaokar, Data Science for IoT professor at Oxford University “Enterprise ...
Ajit Jaokar, Data Science for IoT professor at Oxford University “Enterprise ...Dataconomy Media
 
From Narrow AI to Artificial General Intelligence (AGI)
From Narrow AI to Artificial General Intelligence (AGI)From Narrow AI to Artificial General Intelligence (AGI)
From Narrow AI to Artificial General Intelligence (AGI)Helgi Páll Helgason, PhD
 
Deep Learning Projects - Anomaly Detection Using Deep Learning
Deep Learning Projects - Anomaly Detection Using Deep LearningDeep Learning Projects - Anomaly Detection Using Deep Learning
Deep Learning Projects - Anomaly Detection Using Deep LearningDezyreAcademy
 
Artificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and OverviewArtificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and Overviewbutest
 
Deep learning and neural network converted
Deep learning and neural network convertedDeep learning and neural network converted
Deep learning and neural network convertedJanu Jahnavi
 
Useful Techniques in Artificial Intelligence
Useful Techniques in Artificial IntelligenceUseful Techniques in Artificial Intelligence
Useful Techniques in Artificial IntelligenceIla Group
 
Lecture 02 introduction to ai
Lecture 02 introduction to aiLecture 02 introduction to ai
Lecture 02 introduction to aiHema Kashyap
 
General introduction to AI ML DL DS
General introduction to AI ML DL DSGeneral introduction to AI ML DL DS
General introduction to AI ML DL DSRoopesh Kohad
 
Past, Present and Future of AI: a Fascinating Journey - Ramon Lopez de Mantar...
Past, Present and Future of AI: a Fascinating Journey - Ramon Lopez de Mantar...Past, Present and Future of AI: a Fascinating Journey - Ramon Lopez de Mantar...
Past, Present and Future of AI: a Fascinating Journey - Ramon Lopez de Mantar...PAPIs.io
 
Hot machine learning topics
Hot machine learning topicsHot machine learning topics
Hot machine learning topicsWriteMyThesis
 

What's hot (20)

Deep Learning in real world @Deep Learning Tokyo
Deep Learning in real world @Deep Learning TokyoDeep Learning in real world @Deep Learning Tokyo
Deep Learning in real world @Deep Learning Tokyo
 
introduction to machin learning
introduction to machin learningintroduction to machin learning
introduction to machin learning
 
What is Deep Learning?
What is Deep Learning?What is Deep Learning?
What is Deep Learning?
 
True Artificial Intelligence Will Change Everything
True Artificial Intelligence Will Change Everything True Artificial Intelligence Will Change Everything
True Artificial Intelligence Will Change Everything
 
A quick peek into the word of AI
A quick peek into the word of AIA quick peek into the word of AI
A quick peek into the word of AI
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 
Demystifying Ml, DL and AI
Demystifying Ml, DL and AIDemystifying Ml, DL and AI
Demystifying Ml, DL and AI
 
Fundamentals of Artificial Intelligence — QU AIO Leadership in AI
Fundamentals of Artificial Intelligence — QU AIO Leadership in AIFundamentals of Artificial Intelligence — QU AIO Leadership in AI
Fundamentals of Artificial Intelligence — QU AIO Leadership in AI
 
Ajit Jaokar, Data Science for IoT professor at Oxford University “Enterprise ...
Ajit Jaokar, Data Science for IoT professor at Oxford University “Enterprise ...Ajit Jaokar, Data Science for IoT professor at Oxford University “Enterprise ...
Ajit Jaokar, Data Science for IoT professor at Oxford University “Enterprise ...
 
Machine Learning for dummies!
Machine Learning for dummies!Machine Learning for dummies!
Machine Learning for dummies!
 
From Narrow AI to Artificial General Intelligence (AGI)
From Narrow AI to Artificial General Intelligence (AGI)From Narrow AI to Artificial General Intelligence (AGI)
From Narrow AI to Artificial General Intelligence (AGI)
 
Deep Learning Projects - Anomaly Detection Using Deep Learning
Deep Learning Projects - Anomaly Detection Using Deep LearningDeep Learning Projects - Anomaly Detection Using Deep Learning
Deep Learning Projects - Anomaly Detection Using Deep Learning
 
Artificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and OverviewArtificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and Overview
 
Deep learning and neural network converted
Deep learning and neural network convertedDeep learning and neural network converted
Deep learning and neural network converted
 
Useful Techniques in Artificial Intelligence
Useful Techniques in Artificial IntelligenceUseful Techniques in Artificial Intelligence
Useful Techniques in Artificial Intelligence
 
Lecture 02 introduction to ai
Lecture 02 introduction to aiLecture 02 introduction to ai
Lecture 02 introduction to ai
 
General introduction to AI ML DL DS
General introduction to AI ML DL DSGeneral introduction to AI ML DL DS
General introduction to AI ML DL DS
 
Introduction to AI
Introduction to AIIntroduction to AI
Introduction to AI
 
Past, Present and Future of AI: a Fascinating Journey - Ramon Lopez de Mantar...
Past, Present and Future of AI: a Fascinating Journey - Ramon Lopez de Mantar...Past, Present and Future of AI: a Fascinating Journey - Ramon Lopez de Mantar...
Past, Present and Future of AI: a Fascinating Journey - Ramon Lopez de Mantar...
 
Hot machine learning topics
Hot machine learning topicsHot machine learning topics
Hot machine learning topics
 

Similar to Deep Learning

What is Deep Learning?
What is Deep Learning?What is Deep Learning?
What is Deep Learning?Ahmed Banafa
 
Industrial training (Artificial Intelligence, Machine Learning & Deep Learnin...
Industrial training (Artificial Intelligence, Machine Learning & Deep Learnin...Industrial training (Artificial Intelligence, Machine Learning & Deep Learnin...
Industrial training (Artificial Intelligence, Machine Learning & Deep Learnin...APJ ABDUL KALAM TECHNICAL UNIVERSITY
 
The upsurge of deep learning for computer vision applications
The upsurge of deep learning for computer vision applicationsThe upsurge of deep learning for computer vision applications
The upsurge of deep learning for computer vision applicationsIJECEIAES
 
Nathan benaich The evolving AI marketplace: from startups to the giants
Nathan benaich The evolving AI marketplace:  from startups to the giantsNathan benaich The evolving AI marketplace:  from startups to the giants
Nathan benaich The evolving AI marketplace: from startups to the giantsSudeep Sakalle
 
Unraveling Information about Deep Learning
Unraveling Information about Deep LearningUnraveling Information about Deep Learning
Unraveling Information about Deep LearningIRJET Journal
 
Week3-Deep Neural Network (DNN).pptx
Week3-Deep Neural Network (DNN).pptxWeek3-Deep Neural Network (DNN).pptx
Week3-Deep Neural Network (DNN).pptxfahmi324663
 
Human Emotion Recognition using Machine Learning
Human Emotion Recognition using Machine LearningHuman Emotion Recognition using Machine Learning
Human Emotion Recognition using Machine Learningijtsrd
 
Practical deepllearningv1
Practical deepllearningv1Practical deepllearningv1
Practical deepllearningv1arthi v
 
Exploring Advanced Deep Learning Projects.pdf
Exploring Advanced Deep Learning Projects.pdfExploring Advanced Deep Learning Projects.pdf
Exploring Advanced Deep Learning Projects.pdfprakashdm2024
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Grigory Sapunov
 
History of AI - Presentation by Sanjay Kumar
History of AI - Presentation by Sanjay KumarHistory of AI - Presentation by Sanjay Kumar
History of AI - Presentation by Sanjay KumarSanjay Kumar
 
Deep Learning for AI - Yoshua Bengio, Mila
Deep Learning for AI - Yoshua Bengio, MilaDeep Learning for AI - Yoshua Bengio, Mila
Deep Learning for AI - Yoshua Bengio, MilaLucidworks
 

Similar to Deep Learning (20)

What is Deep Learning?
What is Deep Learning?What is Deep Learning?
What is Deep Learning?
 
Report.pdf
Report.pdfReport.pdf
Report.pdf
 
Industrial training (Artificial Intelligence, Machine Learning & Deep Learnin...
Industrial training (Artificial Intelligence, Machine Learning & Deep Learnin...Industrial training (Artificial Intelligence, Machine Learning & Deep Learnin...
Industrial training (Artificial Intelligence, Machine Learning & Deep Learnin...
 
The upsurge of deep learning for computer vision applications
The upsurge of deep learning for computer vision applicationsThe upsurge of deep learning for computer vision applications
The upsurge of deep learning for computer vision applications
 
Nathan benaich The evolving AI marketplace: from startups to the giants
Nathan benaich The evolving AI marketplace:  from startups to the giantsNathan benaich The evolving AI marketplace:  from startups to the giants
Nathan benaich The evolving AI marketplace: from startups to the giants
 
Deep Neural Networks (DNN)
Deep Neural Networks (DNN)Deep Neural Networks (DNN)
Deep Neural Networks (DNN)
 
Ml vs dl
Ml vs dlMl vs dl
Ml vs dl
 
Ml vs dl
Ml vs dlMl vs dl
Ml vs dl
 
Deep Learning
Deep LearningDeep Learning
Deep Learning
 
Unraveling Information about Deep Learning
Unraveling Information about Deep LearningUnraveling Information about Deep Learning
Unraveling Information about Deep Learning
 
Deep learning
Deep learning Deep learning
Deep learning
 
Week3-Deep Neural Network (DNN).pptx
Week3-Deep Neural Network (DNN).pptxWeek3-Deep Neural Network (DNN).pptx
Week3-Deep Neural Network (DNN).pptx
 
Human Emotion Recognition using Machine Learning
Human Emotion Recognition using Machine LearningHuman Emotion Recognition using Machine Learning
Human Emotion Recognition using Machine Learning
 
Practical deepllearningv1
Practical deepllearningv1Practical deepllearningv1
Practical deepllearningv1
 
Exploring Advanced Deep Learning Projects.pdf
Exploring Advanced Deep Learning Projects.pdfExploring Advanced Deep Learning Projects.pdf
Exploring Advanced Deep Learning Projects.pdf
 
Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016Deep Learning and the state of AI / 2016
Deep Learning and the state of AI / 2016
 
Deep Learning Demystified
Deep Learning DemystifiedDeep Learning Demystified
Deep Learning Demystified
 
History of AI - Presentation by Sanjay Kumar
History of AI - Presentation by Sanjay KumarHistory of AI - Presentation by Sanjay Kumar
History of AI - Presentation by Sanjay Kumar
 
History of AI
History of AIHistory of AI
History of AI
 
Deep Learning for AI - Yoshua Bengio, Mila
Deep Learning for AI - Yoshua Bengio, MilaDeep Learning for AI - Yoshua Bengio, Mila
Deep Learning for AI - Yoshua Bengio, Mila
 

More from Riri Kusumarani

COVID-19 As Catalyst For Information System Publication
COVID-19 As Catalyst For Information System PublicationCOVID-19 As Catalyst For Information System Publication
COVID-19 As Catalyst For Information System PublicationRiri Kusumarani
 
Towards a Smart and Inclusive IKN : A Photovoice Approach
Towards a Smart and Inclusive IKN  : A Photovoice ApproachTowards a Smart and Inclusive IKN  : A Photovoice Approach
Towards a Smart and Inclusive IKN : A Photovoice ApproachRiri Kusumarani
 
Digitalisasi Sistem Manajemen Keamanan di BPPT Pada Era Pandemi
Digitalisasi Sistem Manajemen Keamanan di BPPT Pada Era PandemiDigitalisasi Sistem Manajemen Keamanan di BPPT Pada Era Pandemi
Digitalisasi Sistem Manajemen Keamanan di BPPT Pada Era PandemiRiri Kusumarani
 
GSDV - Global Seoul Forum 2020
GSDV - Global Seoul Forum 2020GSDV - Global Seoul Forum 2020
GSDV - Global Seoul Forum 2020Riri Kusumarani
 
Exploring digital fake news phenomenon in indonesia cpr south_short_pdf
Exploring digital fake news phenomenon in indonesia cpr south_short_pdfExploring digital fake news phenomenon in indonesia cpr south_short_pdf
Exploring digital fake news phenomenon in indonesia cpr south_short_pdfRiri Kusumarani
 
Supply Chain 4.0 and its Potential application in the Dairy Industry
Supply Chain 4.0 and its Potential application in the Dairy IndustrySupply Chain 4.0 and its Potential application in the Dairy Industry
Supply Chain 4.0 and its Potential application in the Dairy IndustryRiri Kusumarani
 
E-HealthCare in Indonesia
E-HealthCare in IndonesiaE-HealthCare in Indonesia
E-HealthCare in IndonesiaRiri Kusumarani
 
NAUTO & Preteckt Business Model
NAUTO & Preteckt Business Model NAUTO & Preteckt Business Model
NAUTO & Preteckt Business Model Riri Kusumarani
 
"Shaping agility through digital options: Reconceptualizing the role of infor...
"Shaping agility through digital options: Reconceptualizing the role of infor..."Shaping agility through digital options: Reconceptualizing the role of infor...
"Shaping agility through digital options: Reconceptualizing the role of infor...Riri Kusumarani
 
A Review of The IT Outsourcing Literature
A Review of The IT Outsourcing LiteratureA Review of The IT Outsourcing Literature
A Review of The IT Outsourcing LiteratureRiri Kusumarani
 
IT governance in the public sector: a conceptual model
IT governance in the public sector: a conceptual modelIT governance in the public sector: a conceptual model
IT governance in the public sector: a conceptual modelRiri Kusumarani
 
It alignment : what have we learned
It alignment : what have we learnedIt alignment : what have we learned
It alignment : what have we learnedRiri Kusumarani
 
The effect of Digital sharing Technologies on Music Markets : A survival anal...
The effect of Digital sharing Technologies on Music Markets : A survival anal...The effect of Digital sharing Technologies on Music Markets : A survival anal...
The effect of Digital sharing Technologies on Music Markets : A survival anal...Riri Kusumarani
 
KAIST GCC : Regional Hub Explorer
KAIST GCC : Regional Hub ExplorerKAIST GCC : Regional Hub Explorer
KAIST GCC : Regional Hub ExplorerRiri Kusumarani
 
Introduction to KAIST GCC
Introduction to KAIST GCCIntroduction to KAIST GCC
Introduction to KAIST GCCRiri Kusumarani
 
CrowdSmart Parking System
CrowdSmart Parking SystemCrowdSmart Parking System
CrowdSmart Parking SystemRiri Kusumarani
 
[Case Study] CSI and fingerprinting case study and discussion assignment
[Case Study] CSI and fingerprinting case study and discussion assignment[Case Study] CSI and fingerprinting case study and discussion assignment
[Case Study] CSI and fingerprinting case study and discussion assignmentRiri Kusumarani
 
[Case Study] Launching Innocent + Developing a new product for the teeth whit...
[Case Study] Launching Innocent + Developing a new product for the teeth whit...[Case Study] Launching Innocent + Developing a new product for the teeth whit...
[Case Study] Launching Innocent + Developing a new product for the teeth whit...Riri Kusumarani
 
[Case Study] And The Winner is Sony's Blu-ray : The High Definition DVD Forma...
[Case Study] And The Winner is Sony's Blu-ray : The High Definition DVD Forma...[Case Study] And The Winner is Sony's Blu-ray : The High Definition DVD Forma...
[Case Study] And The Winner is Sony's Blu-ray : The High Definition DVD Forma...Riri Kusumarani
 

More from Riri Kusumarani (20)

COVID-19 As Catalyst For Information System Publication
COVID-19 As Catalyst For Information System PublicationCOVID-19 As Catalyst For Information System Publication
COVID-19 As Catalyst For Information System Publication
 
Towards a Smart and Inclusive IKN : A Photovoice Approach
Towards a Smart and Inclusive IKN  : A Photovoice ApproachTowards a Smart and Inclusive IKN  : A Photovoice Approach
Towards a Smart and Inclusive IKN : A Photovoice Approach
 
Digitalisasi Sistem Manajemen Keamanan di BPPT Pada Era Pandemi
Digitalisasi Sistem Manajemen Keamanan di BPPT Pada Era PandemiDigitalisasi Sistem Manajemen Keamanan di BPPT Pada Era Pandemi
Digitalisasi Sistem Manajemen Keamanan di BPPT Pada Era Pandemi
 
GSDV - Global Seoul Forum 2020
GSDV - Global Seoul Forum 2020GSDV - Global Seoul Forum 2020
GSDV - Global Seoul Forum 2020
 
Exploring digital fake news phenomenon in indonesia cpr south_short_pdf
Exploring digital fake news phenomenon in indonesia cpr south_short_pdfExploring digital fake news phenomenon in indonesia cpr south_short_pdf
Exploring digital fake news phenomenon in indonesia cpr south_short_pdf
 
Supply Chain 4.0 and its Potential application in the Dairy Industry
Supply Chain 4.0 and its Potential application in the Dairy IndustrySupply Chain 4.0 and its Potential application in the Dairy Industry
Supply Chain 4.0 and its Potential application in the Dairy Industry
 
E-HealthCare in Indonesia
E-HealthCare in IndonesiaE-HealthCare in Indonesia
E-HealthCare in Indonesia
 
NAUTO & Preteckt Business Model
NAUTO & Preteckt Business Model NAUTO & Preteckt Business Model
NAUTO & Preteckt Business Model
 
"Shaping agility through digital options: Reconceptualizing the role of infor...
"Shaping agility through digital options: Reconceptualizing the role of infor..."Shaping agility through digital options: Reconceptualizing the role of infor...
"Shaping agility through digital options: Reconceptualizing the role of infor...
 
A Review of The IT Outsourcing Literature
A Review of The IT Outsourcing LiteratureA Review of The IT Outsourcing Literature
A Review of The IT Outsourcing Literature
 
IT governance in the public sector: a conceptual model
IT governance in the public sector: a conceptual modelIT governance in the public sector: a conceptual model
IT governance in the public sector: a conceptual model
 
It alignment : what have we learned
It alignment : what have we learnedIt alignment : what have we learned
It alignment : what have we learned
 
The effect of Digital sharing Technologies on Music Markets : A survival anal...
The effect of Digital sharing Technologies on Music Markets : A survival anal...The effect of Digital sharing Technologies on Music Markets : A survival anal...
The effect of Digital sharing Technologies on Music Markets : A survival anal...
 
KAIST GCC : Regional Hub Explorer
KAIST GCC : Regional Hub ExplorerKAIST GCC : Regional Hub Explorer
KAIST GCC : Regional Hub Explorer
 
Introduction to KAIST GCC
Introduction to KAIST GCCIntroduction to KAIST GCC
Introduction to KAIST GCC
 
CrowdSmart Parking System
CrowdSmart Parking SystemCrowdSmart Parking System
CrowdSmart Parking System
 
[Case Study] CSI and fingerprinting case study and discussion assignment
[Case Study] CSI and fingerprinting case study and discussion assignment[Case Study] CSI and fingerprinting case study and discussion assignment
[Case Study] CSI and fingerprinting case study and discussion assignment
 
[Case Study] Launching Innocent + Developing a new product for the teeth whit...
[Case Study] Launching Innocent + Developing a new product for the teeth whit...[Case Study] Launching Innocent + Developing a new product for the teeth whit...
[Case Study] Launching Innocent + Developing a new product for the teeth whit...
 
[Case Study] E-Bay
[Case Study] E-Bay[Case Study] E-Bay
[Case Study] E-Bay
 
[Case Study] And The Winner is Sony's Blu-ray : The High Definition DVD Forma...
[Case Study] And The Winner is Sony's Blu-ray : The High Definition DVD Forma...[Case Study] And The Winner is Sony's Blu-ray : The High Definition DVD Forma...
[Case Study] And The Winner is Sony's Blu-ray : The High Definition DVD Forma...
 

Recently uploaded

What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostZilliz
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfSeasiaInfotech2
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfRankYa
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesVector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesZilliz
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 

Recently uploaded (20)

What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdf
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdf
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesVector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector Databases
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 

Deep Learning

  • 1. DEEP LEARNING ITP810 : KEY TECHNOLOGIES FOR 4TH INDUSTRIAL REVOLUTION, PROF. JONGHEUNG PARK PREPARED BY : RIRI KUSUMARANI / 20155636
  • 2. REPORT CONTENT  Concept of Deep Learning  How Deep Learning Works  Architectures  ImageNet Competition  Application of Deep Learning  Reinforcement Learning
  • 3. DEEP LEARNING  Deep learning is strongly related in machine learning in which it shows us an upward trend since early 2005  There are at least 4 people who are also known as the big four in Deep Learning area. These people are : Geoffrey Hinton, Yan LeCunn,Andrew Ng and Yosua Bengio.  The basic idea about deep learning is the availability of computational power which allow machines to recognize objects and translate speech in real time. If we relate this with previous topic in ITP810, it means deep learning also allows artificial intelligence to get smarter each day. Figure 1 : Trends on Deep Learning & The Big Four Source : ITP810 Class Materials
  • 4. How Deep Learning Works?  Programmers would train a neural network to detect an object or phoneme by blitzing the network with digitized versions of images containing those objects or sound waves containing those phonemes.  If the network didn’t accurately recognize a particular pattern, an algorithm would adjust the weights.  The eventual goal of this training was to get the network to consistently recognize the patterns in speech or sets of images that we humans know say, the phoneme “d” or the image of a dog. Figure 2 : Machine Learning Workflow Source : ITP810 Class Materials
  • 5. DEEP LEARNING ARCHITECTURES  There are many well-known deep learning architectures. Some of these are Convolutional Neural Network , Recurrent Neural Network and Deep Belief Network.  Convolutional Neural Network might be the most famous architecture amongst all and it’s simple to understand. CNN mostly being used for image processing..
  • 6. IMAGENET COMPETITION  ImageNet is an image dataset organized according to the WordNet hierarchy. ImageNet aim to provide on average 1000 images to illustrate each synset. Images of each concept are quality-controlled and human-annotated. ImageNet aims to offer tens of millions of cleanly sorted images for most of the concepts in the WordNet hierarchy.  In accordance with this, ImageNet starts a competition which is done each year since 2010. This competition is also known as ImageNet Large Scale Visual Recognition Challenge (ILSVRC).  The idea of this competition is to allow researchers to compare progress in detection across a wider variety of objects - taking advantage of the quite expensive labeling effort. Another motivation is to measure the progress of computer vision for large scale image indexing for retrieval and annotation. Figure 3 : Exampel of ImageNet Competition Source : Imagenet.net
  • 7. APPLICATION OF DEEP LEARNING  Deep learning allows the application of it to many aspects in daily life.  For example, by using CNN Architecture, machine can detect the movement of human through video, image captioning, visual question answering, semantic segmentation and automatic colorization of black and white images.
  • 8. REINFORCEMENT LEARNING What?  Reinforcement Learning is another branch of machine learning in which it doesn’t rely on examples of correct behavior, goal oriented , maximize a reward signal and there’s existence of trade-off between exploration and exploitation.  The picture on the right summarizes the difference between reinforcement learning with other branches of machine learning such as supervised learning and unsupervised learning.
  • 9. How Reinforcement Learning Works?  There will be at least three main factors in RL: Environment, agent , reward and policy. The main goal for RL is to maximize reward. Figure 4 &5 : How RL Works Source : ITP810 Class Materials
  • 10. ALPHA-GO  If we discuss about artificial intelligence and deep learning, we can’t avoid the recent topic of AlphaGo which happens to be the renowned Deep Learning application.  Prof.Lee spent last hour of his lecture to discuss the logic of AlphaGo which I found very much interesting and relatable with the topic that we’ve been discussing for the last 2 weeks.  During his class, he explain in a way that students who don’t have basic knowledge on deep learning, understand how AlphaGo operates.  The concept of reducing search space is said to be the main feauture and strength of AlphaGo . Even this reduce space sounds simple, the technical requirement behind is complicated.  AlphaGo itself is exposed to millions of games and board position.