SlideShare a Scribd company logo
Machine Learning
Narong Intiruk
Data Scientist, T2P Co,.Ltd.
Begin with
Agenda
• What is Machine Learning?
• How is Machine Learning different from traditional
programming?
• How does it work?
• How to use it?
• Tools
• Resources
What is Machine Learning?
“Field of study that gives computers the ability to learn 

without being explicitly programmed”
- Arthur Samuel, 1959
What is Machine Learning?
Learning
Algorithm
"A computer program is said to learn from experience E with respect to
some class of tasks T and performance measure P if its performance at
tasks in T, as measured by P, improves with experience E."
- Tom M. Mitchell
Cat / Not Cat
this is a cat
E
T
Cat -> Cat : 80%
P
How is Machine Learning different from traditional
programming?
How is Machine Learning different from traditional
programming?
if (eyes == 2) & (legs == 4) & (tail == 1)… then
print “Cat”
“ Cat ”
Traditional programming
Input
Program
Computer
Output
- eyes
- legs
- tail
- …..
- …..
How is Machine Learning different from traditional
programming?
if (eyes == 2) & (legs == 4) & (tail == 1)… then
print “Cat”
“ Cat ”
Traditional programming
Input
Program
Computer
Output
- eyes
- legs
- tail
- …..
- …..
How is Machine Learning different from traditional
programming?
“ Cat ”
Machine Learning
Input
Program
Computer
Output
Cat Recognition
- eyes
- legs
- tail
- …..
- …..
How does it work?
Feature
Extraction
Learning
Algorithm
Evaluation
Optimization
Data
Model
Error
Predicted Value = f(X)
We need f that Predicted Value close to True Value
(X)
(f)
Learning Process
Parameters
f( )=“ Cat ”
f( )=“ Cat ”
What is f()?
How does it work?
Data
Number/Categorical
Age Height Weight Gender
19 160 55 male
25 170 55 male
30 175 60 femal
ImageText
Sound
How does it work?
Feature
Extraction
How does it work?
What are the things that should be considered?
Feature
Extraction
Good BMI Bad BMI
Weight
(X1)
Height
(X2)
Good BMI
Bad BMI
Height Weight good/bad
160 55 good
170 55 bad
175 60 good
.. .. ..
Features Space
How does it work?
Feature
Extraction
How does it work?
Multiple Dimension
Feature
Feature
Extraction
How does it work?
Feature
Extraction
How does it work?
Feature
Extraction
Word Importance
the 0.03
property 0.32
viceroy 0.56
….. …..
How does it work?
Feature
Extraction
Principle
Component
Analysis
Dimensionality Reduction
How does it work?
Feature
Extraction
Automatic Feature Extraction
Using Deep Learning
http://magizbox.com/training/deep_learning/site/introduction/
How does it work?
Hand-Crafted Feature Extraction
Feature
Extraction
Automatic Feature Extraction
by using DNN-Deep Learning
http://magizbox.com/training/deep_learning/site/introduction/
How does it work?
Automatic Feature Extraction
Feature
Extraction
Automatic Feature Extraction
by using CNN-Deep Learning
Image
https://devblogs.nvidia.com/parallelforall/deep-learning-nutshell-core-concepts/
How does it work?
Feature
Extraction
Automatic Feature Extraction
by using RNN-Deep Learning
Text
How does it work?
How does it work?
Learning
Algorithm
Car for achieve the goal!
Framework for learning the target function
How does it work?
Learning
Algorithm
Type of Learning
How does it work?
Learning
Algorithm
Supervised Learning > Classification
( , “Cat”) Learning
Algorithm
Cat Model “Cat”
Is cat or not?
How does it work?
Learning
Algorithm
Supervised Learning > Regression
( , 4.5) Learning
Algorithm
House Price
Model
4.3 M.
What is the price of this house?
How does it work?
Learning
Algorithm
Unsupervised Learning
( ) Learning
Algorithm
House
Grouping
Model
What is the group of this house?
Group 1
How does it work?
Learning
Algorithm
Unsupervised Learning
Group1
Group2
Group3
How does it work?
Learning
Algorithm
Reinforcement Learning
( ) Learning
Algorithm
Flappy Bird
Model
How should I move?
“ Down ”
Reward
(+,-)
How does it work?
Learning
Algorithm
Machine Learning Algorithms
https://en.wikipedia.org/wiki/List_of_machine_learning_concepts
How does it work?
Learning
Algorithm
Tree Based
How does it work?
Learning
Algorithm
Tree Based : Random Forest
How does it work?
Learning
Algorithm
Support Vector Machine
3D Features2D Features
How does it work?
Learning
Algorithm
Neural Network
How does it work?
Learning
Algorithm
Neural Network : Deep Learning
Deep Neural Network (DNN)
How does it work?
Learning
Algorithm
Neural Network : Deep Learning
Convolutional Neural Network (CNN)
How does it work?
Learning
Algorithm
Neural Network : Deep Learning
Recurrent Neural Network(RNN)
How does it work?
Evaluation
Learning
Algorithm
Cat / Not Cat
Model
this is a cat
Cat -> Cat : 200
Cat -> Not Cat : 10
How many is loss?
How does it work?
Optimization
Tuning the car’s engine
How does it work?
Optimization
Parameters Space (W1,W2)
f(X) = X1W1 + X2W2 +b
J is the cost function of Learning Algorithm
How does it work?
Optimization
http://playground.tensorflow.org/
Find the best parameters for the function
bad fair good very good
How to use it?
test
trainX
Y
How to use it?
Feature matrix and Label vector
1 0.2 0.32 -0.93 0.32
2 -0.17 0.32 0.52 -0.93
3 -0.93 -0.17 0.52 -0.17
4 0.32 0.52 -0.17 -0.93
1
0
0
1
X
Y
}Input Output
How to use it?
Feature Extraction : Number/Categorical
no x1 x2 x3 x4
1 0.2 0.32 -0.93 0.32
2 -0.17 0.32 0.52 -0.93
3 -0.93 -0.17 0.52 -0.17
X
}
Age Height Weigh
t
Gender Abnormal
19 160 55 male No
25 170 55 male No
30 120 60 femal Yes
0
0
1
Y
Normal(0)/
Abnormal(1)
Covert categorical to number
and normalize data
How to use it?
Feature Extraction : Text -> Binary Vectors
doc1 : You are so cool
doc2 : You are very bad
doc3 : You are very good
word index
you 0
are 1
so 2
cool 3
very 4
bad 5
good 6
corpus dictionary
doc1 : 0 1 2 3
doc2 : 0 1 4 5
doc3 : 0 1 4 6
Feature index
no x0 x1 x2 x3 x4 x5 x6
1 1 1 1 1 0 0 0
2 1 1 0 0 1 1 0
3 1 1 0 0 1 0 1
Binary Feature Vectors
How to use it?
Feature Extraction : Text -> TF-IDF Vectors
doc1 : You are so cool
doc2 : You are very bad
doc3 : You are very good
word index
you 0
are 1
so 2
cool 3
very 4
bad 5
good 6
corpus dictionary
doc1 : 0 1 2 3
doc2 : 0 1 4 5
doc3 : 0 1 4 6
Feature index
no x0 x1 x2 x3 x4 x5 x6
1 0.1 0.1 0.3 0.3 0 0 0
2 0.1 0.1 0 0 0.2 0.3 0
3 0.1 0.1 0 0 0.2 0 0.3
TF-IDF Feature Vectors
word index
you 0.1
are 0.1
so 0.3
cool 0.3
very 0.2
bad 0.3
good 0.3
corpus TF-IDF
https://en.wikipedia.org/wiki/Tf%E2%80%93idf
How to use it?
Feature Extraction : Text -> Word2Vec
word2Vec model
How to use it?
Feature Extraction : Text -> Word2Vec -> Visualize
How to use it?
Feature Extraction : Image -> Pixel Vector
gray scale image (MxN) normalized image matrix (MxN)
[0,0,0,..,0.6,0.5,0,0,0,0,0,0,0,0,0……..0]
pixel1
pixelMxN
Pixel Vector
How to use it?
Feature Extraction : Image -> Pixel Vector
[0,0,0,..,0.6,0.5,0,0,0,0,0,0,0,0,0……..0]image1
Deep Neural Network
How to use it?
Feature Extraction : Image -> raw / gray scale image
raw image
1
2
3
4
5
Convolutional Neural Network
http://cs.stanford.edu/people/karpathy/convnetjs/
How to use it?
Model Evaluation
Confusion Matrix
How to use it?
Model Evaluation
Confusion Matrix Example
Normal Abnormal
Predict Normal 90 10
Predict Abnormal 10 90
Precision = 90/(90 + 10) = 0.9
Recall = 90/(90 + 10) = 0.9
Acc = (90+90)/(90+10+90+10) = 0.9
How to use it?
Model Evaluation : Underfitting and Overfitting
Good on training set but
bad on test set
Bad on training set 

and test set
Good on training set 

and test set
How to use it?
cluster
number
Unsupervised Learning Workflow
How to use it?
Evaluation
Sum of squared erros
Tools
Data Preparation
Machine Learning
Deep Learning
Keras
Data Visualization
scikit-learn
Resources
http://scikit-learn.org/stable/
https://keras.io/
https://www.tensorflow.org/
http://cs.stanford.edu/people/karpathy/convnetjs/
https://www.coursera.org/learn/machine-learning
[DeepLearning.TV]
https://www.youtube.com/channel/UC9OeZkIwhzfv-_Cb7fCikLQ
http://machinelearningmastery.com/introduction-python-deep-learning-library-keras/
[Deep Learning Summer School 2016]
https://www.youtube.com/playlist?list=PLWtzrfzH7gsfxTs8neTRJDXuqAn7qeV4E
http://courses.washington.edu/css490/2012.Winter/lecture_slides/02_math_essentials.pdf
[Deep learning at Oxford 2015]
https://www.youtube.com/playlist?list=PLE6Wd9FR--EfW8dtjAuPoTuPcqmOV53Fu

More Related Content

What's hot

Python fundamentals - basic | WeiYuan
Python fundamentals - basic | WeiYuanPython fundamentals - basic | WeiYuan
Python fundamentals - basic | WeiYuan
Wei-Yuan Chang
 
Python Puzzlers - 2016 Edition
Python Puzzlers - 2016 EditionPython Puzzlers - 2016 Edition
Python Puzzlers - 2016 Edition
Nandan Sawant
 
Machine Learning at Geeky Base 2
Machine Learning at Geeky Base 2Machine Learning at Geeky Base 2
Machine Learning at Geeky Base 2
Kan Ouivirach, Ph.D.
 
Learn python - for beginners - part-2
Learn python - for beginners - part-2Learn python - for beginners - part-2
Learn python - for beginners - part-2
RajKumar Rampelli
 
Python Tricks That You Can't Live Without
Python Tricks That You Can't Live WithoutPython Tricks That You Can't Live Without
Python Tricks That You Can't Live Without
Audrey Roy
 
หัดเขียน A.I. แบบ AlphaGo กันชิวๆ
หัดเขียน A.I. แบบ AlphaGo กันชิวๆหัดเขียน A.I. แบบ AlphaGo กันชิวๆ
หัดเขียน A.I. แบบ AlphaGo กันชิวๆ
Kan Ouivirach, Ph.D.
 
Learn 90% of Python in 90 Minutes
Learn 90% of Python in 90 MinutesLearn 90% of Python in 90 Minutes
Learn 90% of Python in 90 Minutes
Matt Harrison
 
How to Become a Tree Hugger: Random Forests and Predictive Modeling for Devel...
How to Become a Tree Hugger: Random Forests and Predictive Modeling for Devel...How to Become a Tree Hugger: Random Forests and Predictive Modeling for Devel...
How to Become a Tree Hugger: Random Forests and Predictive Modeling for Devel...
Matt Harrison
 
Analysis of Fatal Utah Avalanches with Python. From Scraping, Analysis, to In...
Analysis of Fatal Utah Avalanches with Python. From Scraping, Analysis, to In...Analysis of Fatal Utah Avalanches with Python. From Scraping, Analysis, to In...
Analysis of Fatal Utah Avalanches with Python. From Scraping, Analysis, to In...
Matt Harrison
 
Machine Learning at Geeky Base
Machine Learning at Geeky BaseMachine Learning at Geeky Base
Machine Learning at Geeky Base
Kan Ouivirach, Ph.D.
 
Pa1 session 3_slides
Pa1 session 3_slidesPa1 session 3_slides
Pa1 session 3_slides
aiclub_slides
 
Basics of Python programming (part 2)
Basics of Python programming (part 2)Basics of Python programming (part 2)
Basics of Python programming (part 2)
Pedro Rodrigues
 
AmI 2015 - Python basics
AmI 2015 - Python basicsAmI 2015 - Python basics
AmI 2015 - Python basics
Luigi De Russis
 
Python Tutorial
Python TutorialPython Tutorial
Python Tutorial
Eueung Mulyana
 
Computer notes - data structures
Computer notes - data structuresComputer notes - data structures
Computer notes - data structures
ecomputernotes
 
Benchy: Lightweight framework for Performance Benchmarks
Benchy: Lightweight framework for Performance Benchmarks Benchy: Lightweight framework for Performance Benchmarks
Benchy: Lightweight framework for Performance Benchmarks
Marcel Caraciolo
 
Beginners python cheat sheet - Basic knowledge
Beginners python cheat sheet - Basic knowledge Beginners python cheat sheet - Basic knowledge
Beginners python cheat sheet - Basic knowledge
O T
 
python beginner talk slide
python beginner talk slidepython beginner talk slide
python beginner talk slide
jonycse
 
Introduction to Python and TensorFlow
Introduction to Python and TensorFlowIntroduction to Python and TensorFlow
Introduction to Python and TensorFlow
Bayu Aldi Yansyah
 

What's hot (20)

Python fundamentals - basic | WeiYuan
Python fundamentals - basic | WeiYuanPython fundamentals - basic | WeiYuan
Python fundamentals - basic | WeiYuan
 
Python Puzzlers - 2016 Edition
Python Puzzlers - 2016 EditionPython Puzzlers - 2016 Edition
Python Puzzlers - 2016 Edition
 
Machine Learning at Geeky Base 2
Machine Learning at Geeky Base 2Machine Learning at Geeky Base 2
Machine Learning at Geeky Base 2
 
Learn python - for beginners - part-2
Learn python - for beginners - part-2Learn python - for beginners - part-2
Learn python - for beginners - part-2
 
Python Tricks That You Can't Live Without
Python Tricks That You Can't Live WithoutPython Tricks That You Can't Live Without
Python Tricks That You Can't Live Without
 
หัดเขียน A.I. แบบ AlphaGo กันชิวๆ
หัดเขียน A.I. แบบ AlphaGo กันชิวๆหัดเขียน A.I. แบบ AlphaGo กันชิวๆ
หัดเขียน A.I. แบบ AlphaGo กันชิวๆ
 
Learn 90% of Python in 90 Minutes
Learn 90% of Python in 90 MinutesLearn 90% of Python in 90 Minutes
Learn 90% of Python in 90 Minutes
 
How to Become a Tree Hugger: Random Forests and Predictive Modeling for Devel...
How to Become a Tree Hugger: Random Forests and Predictive Modeling for Devel...How to Become a Tree Hugger: Random Forests and Predictive Modeling for Devel...
How to Become a Tree Hugger: Random Forests and Predictive Modeling for Devel...
 
Analysis of Fatal Utah Avalanches with Python. From Scraping, Analysis, to In...
Analysis of Fatal Utah Avalanches with Python. From Scraping, Analysis, to In...Analysis of Fatal Utah Avalanches with Python. From Scraping, Analysis, to In...
Analysis of Fatal Utah Avalanches with Python. From Scraping, Analysis, to In...
 
Machine Learning at Geeky Base
Machine Learning at Geeky BaseMachine Learning at Geeky Base
Machine Learning at Geeky Base
 
Pa1 session 3_slides
Pa1 session 3_slidesPa1 session 3_slides
Pa1 session 3_slides
 
Basics of Python programming (part 2)
Basics of Python programming (part 2)Basics of Python programming (part 2)
Basics of Python programming (part 2)
 
AmI 2015 - Python basics
AmI 2015 - Python basicsAmI 2015 - Python basics
AmI 2015 - Python basics
 
Python Tutorial
Python TutorialPython Tutorial
Python Tutorial
 
Computer notes - data structures
Computer notes - data structuresComputer notes - data structures
Computer notes - data structures
 
Benchy: Lightweight framework for Performance Benchmarks
Benchy: Lightweight framework for Performance Benchmarks Benchy: Lightweight framework for Performance Benchmarks
Benchy: Lightweight framework for Performance Benchmarks
 
Beginners python cheat sheet - Basic knowledge
Beginners python cheat sheet - Basic knowledge Beginners python cheat sheet - Basic knowledge
Beginners python cheat sheet - Basic knowledge
 
Intro to Python
Intro to PythonIntro to Python
Intro to Python
 
python beginner talk slide
python beginner talk slidepython beginner talk slide
python beginner talk slide
 
Introduction to Python and TensorFlow
Introduction to Python and TensorFlowIntroduction to Python and TensorFlow
Introduction to Python and TensorFlow
 

Viewers also liked

ระบบสารสนเทศและระบบเครือข่าย
ระบบสารสนเทศและระบบเครือข่ายระบบสารสนเทศและระบบเครือข่าย
ระบบสารสนเทศและระบบเครือข่าย
Sassygirl Sassyboy
 
ปัญญาประดิษฐ์กับการศึกษา
ปัญญาประดิษฐ์กับการศึกษาปัญญาประดิษฐ์กับการศึกษา
ปัญญาประดิษฐ์กับการศึกษาapiromrut
 
Begin with Data Scientist
Begin with Data ScientistBegin with Data Scientist
Begin with Data Scientist
Narong Intiruk
 
Fun with Python
Fun with PythonFun with Python
Fun with Python
Narong Intiruk
 
BSidesLV 2013 - Using Machine Learning to Support Information Security
BSidesLV 2013 - Using Machine Learning to Support Information SecurityBSidesLV 2013 - Using Machine Learning to Support Information Security
BSidesLV 2013 - Using Machine Learning to Support Information Security
Alex Pinto
 
Python as the Zen of Data Science
Python as the Zen of Data SciencePython as the Zen of Data Science
Python as the Zen of Data Science
Travis Oliphant
 
Building a performing Machine Learning model from A to Z
Building a performing Machine Learning model from A to ZBuilding a performing Machine Learning model from A to Z
Building a performing Machine Learning model from A to Z
Charles Vestur
 
Tensorflow - Intro (2017)
Tensorflow - Intro (2017)Tensorflow - Intro (2017)
Tensorflow - Intro (2017)
Alessio Tonioni
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine LearningLior Rokach
 

Viewers also liked (9)

ระบบสารสนเทศและระบบเครือข่าย
ระบบสารสนเทศและระบบเครือข่ายระบบสารสนเทศและระบบเครือข่าย
ระบบสารสนเทศและระบบเครือข่าย
 
ปัญญาประดิษฐ์กับการศึกษา
ปัญญาประดิษฐ์กับการศึกษาปัญญาประดิษฐ์กับการศึกษา
ปัญญาประดิษฐ์กับการศึกษา
 
Begin with Data Scientist
Begin with Data ScientistBegin with Data Scientist
Begin with Data Scientist
 
Fun with Python
Fun with PythonFun with Python
Fun with Python
 
BSidesLV 2013 - Using Machine Learning to Support Information Security
BSidesLV 2013 - Using Machine Learning to Support Information SecurityBSidesLV 2013 - Using Machine Learning to Support Information Security
BSidesLV 2013 - Using Machine Learning to Support Information Security
 
Python as the Zen of Data Science
Python as the Zen of Data SciencePython as the Zen of Data Science
Python as the Zen of Data Science
 
Building a performing Machine Learning model from A to Z
Building a performing Machine Learning model from A to ZBuilding a performing Machine Learning model from A to Z
Building a performing Machine Learning model from A to Z
 
Tensorflow - Intro (2017)
Tensorflow - Intro (2017)Tensorflow - Intro (2017)
Tensorflow - Intro (2017)
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 

Similar to Begin with Machine Learning

2020 04 04 NetCoreConf - Machine Learning.Net
2020 04 04 NetCoreConf - Machine Learning.Net2020 04 04 NetCoreConf - Machine Learning.Net
2020 04 04 NetCoreConf - Machine Learning.Net
Bruno Capuano
 
Data oriented design and c++
Data oriented design and c++Data oriented design and c++
Data oriented design and c++
Mike Acton
 
2020 04 10 Catch IT - Getting started with ML.Net
2020 04 10 Catch IT - Getting started with ML.Net2020 04 10 Catch IT - Getting started with ML.Net
2020 04 10 Catch IT - Getting started with ML.Net
Bruno Capuano
 
Machine Learning from a Software Engineer's perspective
Machine Learning from a Software Engineer's perspectiveMachine Learning from a Software Engineer's perspective
Machine Learning from a Software Engineer's perspective
Marijn van Zelst
 
Machine learning from a software engineer's perspective - Marijn van Zelst - ...
Machine learning from a software engineer's perspective - Marijn van Zelst - ...Machine learning from a software engineer's perspective - Marijn van Zelst - ...
Machine learning from a software engineer's perspective - Marijn van Zelst - ...
Codemotion
 
Meetup 29042015
Meetup 29042015Meetup 29042015
Meetup 29042015lbishal
 
Strata London - Deep Learning 05-2015
Strata London - Deep Learning 05-2015Strata London - Deep Learning 05-2015
Strata London - Deep Learning 05-2015
Turi, Inc.
 
2019 12 19 Mississauga .Net User Group - Machine Learning.Net and Auto ML
2019 12 19 Mississauga .Net User Group - Machine Learning.Net and Auto ML2019 12 19 Mississauga .Net User Group - Machine Learning.Net and Auto ML
2019 12 19 Mississauga .Net User Group - Machine Learning.Net and Auto ML
Bruno Capuano
 
2018 Global Azure Bootcamp Azure Machine Learning for neural networks
2018 Global Azure Bootcamp Azure Machine Learning for neural networks2018 Global Azure Bootcamp Azure Machine Learning for neural networks
2018 Global Azure Bootcamp Azure Machine Learning for neural networks
Setu Chokshi
 
Mat lab workshop
Mat lab workshopMat lab workshop
Mat lab workshop
Vinay Kumar
 
2020 02 29 TechDay Conf - Getting started with Machine Learning.Net
2020 02 29 TechDay Conf - Getting started with Machine Learning.Net2020 02 29 TechDay Conf - Getting started with Machine Learning.Net
2020 02 29 TechDay Conf - Getting started with Machine Learning.Net
Bruno Capuano
 
2020 09 24 - CONDG ML.Net
2020 09 24 - CONDG ML.Net2020 09 24 - CONDG ML.Net
2020 09 24 - CONDG ML.Net
Bruno Capuano
 
Real-time Face Recognition & Detection Systems 1
Real-time Face Recognition & Detection Systems 1Real-time Face Recognition & Detection Systems 1
Real-time Face Recognition & Detection Systems 1Suvadip Shome
 
Deep learning
Deep learningDeep learning
Deep learning
Alessio Palma
 
2019 09 05 Global AI Night Toronto - Machine Learning.Net
2019 09 05 Global AI Night Toronto - Machine Learning.Net2019 09 05 Global AI Night Toronto - Machine Learning.Net
2019 09 05 Global AI Night Toronto - Machine Learning.Net
Bruno Capuano
 
Automate ml workflow_transmogrif_ai-_chetan_khatri_berlin-scala
Automate ml workflow_transmogrif_ai-_chetan_khatri_berlin-scalaAutomate ml workflow_transmogrif_ai-_chetan_khatri_berlin-scala
Automate ml workflow_transmogrif_ai-_chetan_khatri_berlin-scala
Chetan Khatri
 
Startup Jungle Cambodia | How to Build your First Machine Learning Application
Startup Jungle Cambodia | How to Build your First Machine Learning ApplicationStartup Jungle Cambodia | How to Build your First Machine Learning Application
Startup Jungle Cambodia | How to Build your First Machine Learning Application
Slash
 
Feature Engineering - Getting most out of data for predictive models - TDC 2017
Feature Engineering - Getting most out of data for predictive models - TDC 2017Feature Engineering - Getting most out of data for predictive models - TDC 2017
Feature Engineering - Getting most out of data for predictive models - TDC 2017
Gabriel Moreira
 
TransmogrifAI - Automate Machine Learning Workflow with the power of Scala an...
TransmogrifAI - Automate Machine Learning Workflow with the power of Scala an...TransmogrifAI - Automate Machine Learning Workflow with the power of Scala an...
TransmogrifAI - Automate Machine Learning Workflow with the power of Scala an...
Chetan Khatri
 
Apprentissage statistique et analyse prédictive en Python avec scikit-learn p...
Apprentissage statistique et analyse prédictive en Python avec scikit-learn p...Apprentissage statistique et analyse prédictive en Python avec scikit-learn p...
Apprentissage statistique et analyse prédictive en Python avec scikit-learn p...
La Cuisine du Web
 

Similar to Begin with Machine Learning (20)

2020 04 04 NetCoreConf - Machine Learning.Net
2020 04 04 NetCoreConf - Machine Learning.Net2020 04 04 NetCoreConf - Machine Learning.Net
2020 04 04 NetCoreConf - Machine Learning.Net
 
Data oriented design and c++
Data oriented design and c++Data oriented design and c++
Data oriented design and c++
 
2020 04 10 Catch IT - Getting started with ML.Net
2020 04 10 Catch IT - Getting started with ML.Net2020 04 10 Catch IT - Getting started with ML.Net
2020 04 10 Catch IT - Getting started with ML.Net
 
Machine Learning from a Software Engineer's perspective
Machine Learning from a Software Engineer's perspectiveMachine Learning from a Software Engineer's perspective
Machine Learning from a Software Engineer's perspective
 
Machine learning from a software engineer's perspective - Marijn van Zelst - ...
Machine learning from a software engineer's perspective - Marijn van Zelst - ...Machine learning from a software engineer's perspective - Marijn van Zelst - ...
Machine learning from a software engineer's perspective - Marijn van Zelst - ...
 
Meetup 29042015
Meetup 29042015Meetup 29042015
Meetup 29042015
 
Strata London - Deep Learning 05-2015
Strata London - Deep Learning 05-2015Strata London - Deep Learning 05-2015
Strata London - Deep Learning 05-2015
 
2019 12 19 Mississauga .Net User Group - Machine Learning.Net and Auto ML
2019 12 19 Mississauga .Net User Group - Machine Learning.Net and Auto ML2019 12 19 Mississauga .Net User Group - Machine Learning.Net and Auto ML
2019 12 19 Mississauga .Net User Group - Machine Learning.Net and Auto ML
 
2018 Global Azure Bootcamp Azure Machine Learning for neural networks
2018 Global Azure Bootcamp Azure Machine Learning for neural networks2018 Global Azure Bootcamp Azure Machine Learning for neural networks
2018 Global Azure Bootcamp Azure Machine Learning for neural networks
 
Mat lab workshop
Mat lab workshopMat lab workshop
Mat lab workshop
 
2020 02 29 TechDay Conf - Getting started with Machine Learning.Net
2020 02 29 TechDay Conf - Getting started with Machine Learning.Net2020 02 29 TechDay Conf - Getting started with Machine Learning.Net
2020 02 29 TechDay Conf - Getting started with Machine Learning.Net
 
2020 09 24 - CONDG ML.Net
2020 09 24 - CONDG ML.Net2020 09 24 - CONDG ML.Net
2020 09 24 - CONDG ML.Net
 
Real-time Face Recognition & Detection Systems 1
Real-time Face Recognition & Detection Systems 1Real-time Face Recognition & Detection Systems 1
Real-time Face Recognition & Detection Systems 1
 
Deep learning
Deep learningDeep learning
Deep learning
 
2019 09 05 Global AI Night Toronto - Machine Learning.Net
2019 09 05 Global AI Night Toronto - Machine Learning.Net2019 09 05 Global AI Night Toronto - Machine Learning.Net
2019 09 05 Global AI Night Toronto - Machine Learning.Net
 
Automate ml workflow_transmogrif_ai-_chetan_khatri_berlin-scala
Automate ml workflow_transmogrif_ai-_chetan_khatri_berlin-scalaAutomate ml workflow_transmogrif_ai-_chetan_khatri_berlin-scala
Automate ml workflow_transmogrif_ai-_chetan_khatri_berlin-scala
 
Startup Jungle Cambodia | How to Build your First Machine Learning Application
Startup Jungle Cambodia | How to Build your First Machine Learning ApplicationStartup Jungle Cambodia | How to Build your First Machine Learning Application
Startup Jungle Cambodia | How to Build your First Machine Learning Application
 
Feature Engineering - Getting most out of data for predictive models - TDC 2017
Feature Engineering - Getting most out of data for predictive models - TDC 2017Feature Engineering - Getting most out of data for predictive models - TDC 2017
Feature Engineering - Getting most out of data for predictive models - TDC 2017
 
TransmogrifAI - Automate Machine Learning Workflow with the power of Scala an...
TransmogrifAI - Automate Machine Learning Workflow with the power of Scala an...TransmogrifAI - Automate Machine Learning Workflow with the power of Scala an...
TransmogrifAI - Automate Machine Learning Workflow with the power of Scala an...
 
Apprentissage statistique et analyse prédictive en Python avec scikit-learn p...
Apprentissage statistique et analyse prédictive en Python avec scikit-learn p...Apprentissage statistique et analyse prédictive en Python avec scikit-learn p...
Apprentissage statistique et analyse prédictive en Python avec scikit-learn p...
 

Recently uploaded

Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
nkrafacyberclub
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
Alpen-Adria-Universität
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
Enhancing Performance with Globus and the Science DMZ
Enhancing Performance with Globus and the Science DMZEnhancing Performance with Globus and the Science DMZ
Enhancing Performance with Globus and the Science DMZ
Globus
 
Introduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - CybersecurityIntroduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - Cybersecurity
mikeeftimakis1
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...
sonjaschweigert1
 
Assure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyesAssure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
UiPath Community Day Dubai: AI at Work..
UiPath Community Day Dubai: AI at Work..UiPath Community Day Dubai: AI at Work..
UiPath Community Day Dubai: AI at Work..
UiPathCommunity
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
SOFTTECHHUB
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
OnBoard
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Nexer Digital
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
Ralf Eggert
 

Recently uploaded (20)

Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
Enhancing Performance with Globus and the Science DMZ
Enhancing Performance with Globus and the Science DMZEnhancing Performance with Globus and the Science DMZ
Enhancing Performance with Globus and the Science DMZ
 
Introduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - CybersecurityIntroduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - Cybersecurity
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...
 
Assure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyesAssure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyes
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
UiPath Community Day Dubai: AI at Work..
UiPath Community Day Dubai: AI at Work..UiPath Community Day Dubai: AI at Work..
UiPath Community Day Dubai: AI at Work..
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
 

Begin with Machine Learning

  • 1. Machine Learning Narong Intiruk Data Scientist, T2P Co,.Ltd. Begin with
  • 2. Agenda • What is Machine Learning? • How is Machine Learning different from traditional programming? • How does it work? • How to use it? • Tools • Resources
  • 3. What is Machine Learning? “Field of study that gives computers the ability to learn 
 without being explicitly programmed” - Arthur Samuel, 1959
  • 4. What is Machine Learning? Learning Algorithm "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E." - Tom M. Mitchell Cat / Not Cat this is a cat E T Cat -> Cat : 80% P
  • 5. How is Machine Learning different from traditional programming?
  • 6. How is Machine Learning different from traditional programming? if (eyes == 2) & (legs == 4) & (tail == 1)… then print “Cat” “ Cat ” Traditional programming Input Program Computer Output - eyes - legs - tail - ….. - …..
  • 7. How is Machine Learning different from traditional programming? if (eyes == 2) & (legs == 4) & (tail == 1)… then print “Cat” “ Cat ” Traditional programming Input Program Computer Output - eyes - legs - tail - ….. - …..
  • 8. How is Machine Learning different from traditional programming? “ Cat ” Machine Learning Input Program Computer Output Cat Recognition - eyes - legs - tail - ….. - …..
  • 9. How does it work? Feature Extraction Learning Algorithm Evaluation Optimization Data Model Error Predicted Value = f(X) We need f that Predicted Value close to True Value (X) (f) Learning Process Parameters
  • 10. f( )=“ Cat ” f( )=“ Cat ” What is f()? How does it work?
  • 11. Data Number/Categorical Age Height Weight Gender 19 160 55 male 25 170 55 male 30 175 60 femal ImageText Sound How does it work?
  • 12. Feature Extraction How does it work? What are the things that should be considered?
  • 13. Feature Extraction Good BMI Bad BMI Weight (X1) Height (X2) Good BMI Bad BMI Height Weight good/bad 160 55 good 170 55 bad 175 60 good .. .. .. Features Space How does it work?
  • 14. Feature Extraction How does it work? Multiple Dimension Feature
  • 17. Feature Extraction Word Importance the 0.03 property 0.32 viceroy 0.56 ….. ….. How does it work?
  • 19. Feature Extraction Automatic Feature Extraction Using Deep Learning http://magizbox.com/training/deep_learning/site/introduction/ How does it work? Hand-Crafted Feature Extraction
  • 20. Feature Extraction Automatic Feature Extraction by using DNN-Deep Learning http://magizbox.com/training/deep_learning/site/introduction/ How does it work? Automatic Feature Extraction
  • 21. Feature Extraction Automatic Feature Extraction by using CNN-Deep Learning Image https://devblogs.nvidia.com/parallelforall/deep-learning-nutshell-core-concepts/ How does it work?
  • 22. Feature Extraction Automatic Feature Extraction by using RNN-Deep Learning Text How does it work?
  • 23. How does it work? Learning Algorithm Car for achieve the goal! Framework for learning the target function
  • 24. How does it work? Learning Algorithm Type of Learning
  • 25. How does it work? Learning Algorithm Supervised Learning > Classification ( , “Cat”) Learning Algorithm Cat Model “Cat” Is cat or not?
  • 26. How does it work? Learning Algorithm Supervised Learning > Regression ( , 4.5) Learning Algorithm House Price Model 4.3 M. What is the price of this house?
  • 27. How does it work? Learning Algorithm Unsupervised Learning ( ) Learning Algorithm House Grouping Model What is the group of this house? Group 1
  • 28. How does it work? Learning Algorithm Unsupervised Learning Group1 Group2 Group3
  • 29. How does it work? Learning Algorithm Reinforcement Learning ( ) Learning Algorithm Flappy Bird Model How should I move? “ Down ” Reward (+,-)
  • 30. How does it work? Learning Algorithm Machine Learning Algorithms https://en.wikipedia.org/wiki/List_of_machine_learning_concepts
  • 31. How does it work? Learning Algorithm Tree Based
  • 32. How does it work? Learning Algorithm Tree Based : Random Forest
  • 33. How does it work? Learning Algorithm Support Vector Machine 3D Features2D Features
  • 34. How does it work? Learning Algorithm Neural Network
  • 35. How does it work? Learning Algorithm Neural Network : Deep Learning Deep Neural Network (DNN)
  • 36. How does it work? Learning Algorithm Neural Network : Deep Learning Convolutional Neural Network (CNN)
  • 37. How does it work? Learning Algorithm Neural Network : Deep Learning Recurrent Neural Network(RNN)
  • 38. How does it work? Evaluation Learning Algorithm Cat / Not Cat Model this is a cat Cat -> Cat : 200 Cat -> Not Cat : 10 How many is loss?
  • 39. How does it work? Optimization Tuning the car’s engine
  • 40. How does it work? Optimization Parameters Space (W1,W2) f(X) = X1W1 + X2W2 +b J is the cost function of Learning Algorithm
  • 41. How does it work? Optimization http://playground.tensorflow.org/ Find the best parameters for the function bad fair good very good
  • 42. How to use it? test trainX Y
  • 43. How to use it? Feature matrix and Label vector 1 0.2 0.32 -0.93 0.32 2 -0.17 0.32 0.52 -0.93 3 -0.93 -0.17 0.52 -0.17 4 0.32 0.52 -0.17 -0.93 1 0 0 1 X Y }Input Output
  • 44. How to use it? Feature Extraction : Number/Categorical no x1 x2 x3 x4 1 0.2 0.32 -0.93 0.32 2 -0.17 0.32 0.52 -0.93 3 -0.93 -0.17 0.52 -0.17 X } Age Height Weigh t Gender Abnormal 19 160 55 male No 25 170 55 male No 30 120 60 femal Yes 0 0 1 Y Normal(0)/ Abnormal(1) Covert categorical to number and normalize data
  • 45. How to use it? Feature Extraction : Text -> Binary Vectors doc1 : You are so cool doc2 : You are very bad doc3 : You are very good word index you 0 are 1 so 2 cool 3 very 4 bad 5 good 6 corpus dictionary doc1 : 0 1 2 3 doc2 : 0 1 4 5 doc3 : 0 1 4 6 Feature index no x0 x1 x2 x3 x4 x5 x6 1 1 1 1 1 0 0 0 2 1 1 0 0 1 1 0 3 1 1 0 0 1 0 1 Binary Feature Vectors
  • 46. How to use it? Feature Extraction : Text -> TF-IDF Vectors doc1 : You are so cool doc2 : You are very bad doc3 : You are very good word index you 0 are 1 so 2 cool 3 very 4 bad 5 good 6 corpus dictionary doc1 : 0 1 2 3 doc2 : 0 1 4 5 doc3 : 0 1 4 6 Feature index no x0 x1 x2 x3 x4 x5 x6 1 0.1 0.1 0.3 0.3 0 0 0 2 0.1 0.1 0 0 0.2 0.3 0 3 0.1 0.1 0 0 0.2 0 0.3 TF-IDF Feature Vectors word index you 0.1 are 0.1 so 0.3 cool 0.3 very 0.2 bad 0.3 good 0.3 corpus TF-IDF https://en.wikipedia.org/wiki/Tf%E2%80%93idf
  • 47. How to use it? Feature Extraction : Text -> Word2Vec word2Vec model
  • 48. How to use it? Feature Extraction : Text -> Word2Vec -> Visualize
  • 49. How to use it? Feature Extraction : Image -> Pixel Vector gray scale image (MxN) normalized image matrix (MxN) [0,0,0,..,0.6,0.5,0,0,0,0,0,0,0,0,0……..0] pixel1 pixelMxN Pixel Vector
  • 50. How to use it? Feature Extraction : Image -> Pixel Vector [0,0,0,..,0.6,0.5,0,0,0,0,0,0,0,0,0……..0]image1 Deep Neural Network
  • 51. How to use it? Feature Extraction : Image -> raw / gray scale image raw image 1 2 3 4 5 Convolutional Neural Network http://cs.stanford.edu/people/karpathy/convnetjs/
  • 52. How to use it? Model Evaluation Confusion Matrix
  • 53. How to use it? Model Evaluation Confusion Matrix Example Normal Abnormal Predict Normal 90 10 Predict Abnormal 10 90 Precision = 90/(90 + 10) = 0.9 Recall = 90/(90 + 10) = 0.9 Acc = (90+90)/(90+10+90+10) = 0.9
  • 54. How to use it? Model Evaluation : Underfitting and Overfitting Good on training set but bad on test set Bad on training set 
 and test set Good on training set 
 and test set
  • 55. How to use it? cluster number Unsupervised Learning Workflow
  • 56. How to use it? Evaluation Sum of squared erros
  • 57. Tools Data Preparation Machine Learning Deep Learning Keras Data Visualization scikit-learn
  • 58. Resources http://scikit-learn.org/stable/ https://keras.io/ https://www.tensorflow.org/ http://cs.stanford.edu/people/karpathy/convnetjs/ https://www.coursera.org/learn/machine-learning [DeepLearning.TV] https://www.youtube.com/channel/UC9OeZkIwhzfv-_Cb7fCikLQ http://machinelearningmastery.com/introduction-python-deep-learning-library-keras/ [Deep Learning Summer School 2016] https://www.youtube.com/playlist?list=PLWtzrfzH7gsfxTs8neTRJDXuqAn7qeV4E http://courses.washington.edu/css490/2012.Winter/lecture_slides/02_math_essentials.pdf [Deep learning at Oxford 2015] https://www.youtube.com/playlist?list=PLE6Wd9FR--EfW8dtjAuPoTuPcqmOV53Fu