PyData SF 2016 --- Moving forward through the darkness
-
Upload
chia-chi-chang -
Category
Data & Analytics
-
view
316 -
download
1
Transcript of PyData SF 2016 --- Moving forward through the darkness
![Page 1: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/1.jpg)
Moving Forward ThroughThe Darkness
the blindness of modeling and how to break through
Chia-Chi@PyData SF 2016
![Page 2: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/2.jpg)
![Page 3: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/3.jpg)
About Chia-Chi (George) ● Organizer of Taiwan R User Group and MLDM Monday● 7 years experience in quantitative trading in future & option market● 5 years consultant experience in machine learning & data mining● 4 years experience in e-commerce (consultant & join SaaS teams)● 4 years experience in building of recommendation and search engine ● Volenteer in PyCon APAC 2014 (program officer)● Volenteer in PyCon APAC 2015 (program officer)● I love python and hope I can write python everyday !
![Page 4: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/4.jpg)
Training models from data
is just like scketching pictures from the world
![Page 5: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/5.jpg)
![Page 6: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/6.jpg)
Jackson Pollock:The painting has a life of its own.
I try to let it come through.
![Page 7: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/7.jpg)
As a data scientist … The data has a life of its own. I just try to let it come through.
![Page 8: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/8.jpg)
![Page 9: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/9.jpg)
The first step … is not picking up your pen !
is choosing an angle !and do some observation !
![Page 10: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/10.jpg)
![Page 11: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/11.jpg)
Now, the object you want to sckeching ...is your data!
![Page 12: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/12.jpg)
Try to scketch it : y = a_0 + a_1 x
![Page 13: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/13.jpg)
Which line is the most similar one ?
It depends on you observation angle!
![Page 14: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/14.jpg)
What the angle means ...in a machine learning problem ?
![Page 15: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/15.jpg)
Angle of Linear Regression
![Page 16: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/16.jpg)
![Page 17: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/17.jpg)
![Page 18: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/18.jpg)
![Page 19: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/19.jpg)
After Chose an angle ... You chose the question & the evaluator ...
(as a data scientist)
![Page 20: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/20.jpg)
![Page 21: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/21.jpg)
How to change the angle?
In the Linear Regression Problem
![Page 22: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/22.jpg)
![Page 23: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/23.jpg)
![Page 24: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/24.jpg)
![Page 25: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/25.jpg)
The MetaphorData (the object) +
Evaluator (view of point | angle)=> Model (picture)
![Page 26: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/26.jpg)
![Page 27: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/27.jpg)
Different Angles ... Different Pictures …
(in scketching)
![Page 28: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/28.jpg)
Different questions ... Different models …
(in data science)
![Page 29: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/29.jpg)
Whatever you observe … Whatever you draw !
(both in scketching and data science)
![Page 30: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/30.jpg)
The two keysHelp you apply machine learning
in the real world
![Page 31: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/31.jpg)
Can Learn ONLYThrough Real
Practice
Can Learn fromSchool or Practice
![Page 32: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/32.jpg)
Modeling Procedures:● Choose a Real Problem● Collecting Related Data● Choose a method convert Data to Vectors (or Tensors)● Decompose Real Problem into several ML or Math Problems● Solve each ML or Math Problem individually ● Combine the Solutions of all ML or Math Problems● Check is that truly solve the Real Problem ?
![Page 33: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/33.jpg)
Case Study:How to build
a Recommendation System in News Platform
![Page 34: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/34.jpg)
User-Centered Recommendation
News you probabily also want to read
![Page 35: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/35.jpg)
Platform
Tracking
Users Behavior
Data Feed Response
News Data Results
Machine Learning
Server Group
Server Group
Processing Data Prediction Data
![Page 36: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/36.jpg)
Modeling Procedures -- Part 1:● Problem: how to make users reach more news they want to read ?● Data:
○ News Data (Article)■ Title■ Text■ Time■ Category
○ User Behavior Data ■ User View Post■ User Click Links■ User not Click Links
![Page 37: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/37.jpg)
Modeling Procedures -- Part 2:● Data to Vector (or Tensors)
○ News Data■ TermDocumentMatrix (scikit-learn)■ Word2Vec (gensim word2vec)
○ User Behavior Data ■ Event Sampling (Spark streaming, Kafka, or Traildb)
● construct user-item matrix (user view|click|not-click events)● construct item-item matrix (view-after-view click-after-view ... )● construct user-item-time tensor cube ● construct user-item-item-time tensor cube
![Page 38: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/38.jpg)
Modeling Procedures -- Part 3:● Real to ML (or Math) and Solve ML (or Math) Problems
○ Real Problem: how to make users reach more news they want to read ?○ ML (or Math) Problems:
■ Hottest & Newest ■ Content-Based Relations■ Collaborative Filtering
![Page 39: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/39.jpg)
Newest & Hottest : Sorting
![Page 40: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/40.jpg)
Content-Based Relations: ClusteringWith
TermDocumentMatrix
Or
The results coming from word2vec
![Page 41: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/41.jpg)
![Page 42: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/42.jpg)
![Page 43: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/43.jpg)
![Page 44: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/44.jpg)
Collaborative Filtering: MF & Matrix Completion
![Page 45: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/45.jpg)
Use only 20% data to re-generate full image !
Ref: ipynb@github
![Page 46: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/46.jpg)
Modeling Procedures -- Part 4:● Combine Solutions together and Check it with Real Problem
○ Ensemble Learning (for static combination)○ Reinforcement Learning (for dynamic improvement)
![Page 47: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/47.jpg)
![Page 48: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/48.jpg)
![Page 49: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/49.jpg)
![Page 50: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/50.jpg)
Recap: Modeling Procedures:● Choose a Real Problem● Collecting Related Data● Choose a method convert Data to Vectors (or Tensors)● Decompose Real Problem into several ML or Math Problems● Solve each ML or Math Problem individually ● Combine the Solutions of all ML or Math Problems● Check is that truly solve the Real Problem ?
![Page 51: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/51.jpg)
The Blindnessin the Modeling Procedures
![Page 52: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/52.jpg)
Blindness of Modeling Procedures:
● Choose a Real Problem● Collecting Related Data● Choose a method convert Data to Vectors (or Tensors)● Decompose Real Problem into several ML or Math Problems● Solve each ML or Math Problem individually ● Combine the Solutions of all ML or Math Problems● Check is that truly solve the Real Problem ?
![Page 53: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/53.jpg)
Problem Data
Probelm-Driven:
Thinking Data
Through Problem
Data-Driven:Thinking Problem
Through Data
Problem behind
Problem
Information behind Data
BusinessInsights
![Page 54: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/54.jpg)
The Blindness betweenData and Problem
Is there any related information in that data ?Could the problem answer by this data ?
![Page 55: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/55.jpg)
![Page 56: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/56.jpg)
Case Study: Bookstore Could you use our POS data
to find some methods to convertthose users who originally dislike us?
![Page 57: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/57.jpg)
Case Study: Bookstore Could you use our POS data to find the potential users ?
"potential" means users want to buy itbut they haven't
![Page 58: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/58.jpg)
![Page 59: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/59.jpg)
Data from POSONLY has the information
about converted users
There is no information about disliked and unconverted users
![Page 60: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/60.jpg)
Thinking in Two WaysData-Driven
Problem-Driven
![Page 61: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/61.jpg)
Problem???
POSData
Probelm-Driven:
Thinking Data
Through Problem
Data-Driven:Thinking Problem
Through Data
Problem behind
Problem
Information behind Data
BusinessInsights
![Page 62: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/62.jpg)
Gain Bookstore's Revenue ?
Data???
Probelm-Driven:
Thinking Data
Through Problem
Data-Driven:Thinking Problem
Through Data
Problem behind
Problem
Information behind Data
BusinessInsights
![Page 63: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/63.jpg)
Case Study: LBS Food Search
a story about "delicous" is not delicous !
(this is also the blindness of NLP)
![Page 64: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/64.jpg)
Data ThinkingFirst-Hand Versus Second-Hand
for example, delicous versus "delicous"
![Page 65: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/65.jpg)
Machine could NOT Learn by itself.
It just like a child.It learn by training data !
sometimes would learn badly!
![Page 66: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/66.jpg)
Blindness of Modeling Procedures:● Choose a Real Problem● Collecting Related Data
● Choose a method convert Data to Vectors (or Tensors)
● Decompose Real Problem into several ML or Math Problems● Solve each ML or Math Problem individually ● Combine the Solutions of all ML or Math Problems● Check is that truly solve the Real Problem ?
![Page 67: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/67.jpg)
The Blindness FromData to Vector
Is there any information losing when you are converting your data?
![Page 68: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/68.jpg)
Blindness of unigramI love it (我愛它) = it love me (它愛我)I hate it (我恨它) = it hate me (它恨我)
![Page 69: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/69.jpg)
The Blindness FromMathematical Concept
The gap between math and real world:
When putting the units back to the formula …
![Page 70: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/70.jpg)
Math in Elementary School … The secret behind the minus operator● 103 - 100 = 6 - 3 ?● 103 dollars - 100 dollars = 6 dollars - 3 dollars ?● 103 dollar stock - 100 dollars stock = 6 dollars stock - 3 dollars stock ?
(formula)(units)
● (103 - 100 = 6 - 3) (dollars)● (103 - 100 = 6 - 3) (dollars stock)
How to choose the right coordinate for stock price ?
![Page 71: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/71.jpg)
Blindness of Modeling Procedures:● Choose a Real Problem● Collecting Related Data● Choose a method convert Data to Vectors (or Tensors)
● Decompose Real Problem into several ML or Math Problems
● Solve each ML or Math Problem individually ● Combine the Solutions of all ML or Math Problems● Check is that truly solve the Real Problem ?
![Page 72: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/72.jpg)
The Blindness FromML Frameworks
Classification & Clustering
![Page 73: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/73.jpg)
When orange-apple classifier meet an banana?
![Page 74: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/74.jpg)
When a digital classifier meet an alphabet ?
A -> 9
![Page 75: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/75.jpg)
The blindness of clustering methods
![Page 76: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/76.jpg)
Cannot force two points in the same cluster
![Page 77: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/77.jpg)
The fact is … We always get some data with labels
But some without
(1) How to propograte labels ?(2) How to detect new labels with labelers?
![Page 78: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/78.jpg)
New Data & New Labelsare coming all the way
In e-commerce retailers &In news platforms
![Page 79: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/79.jpg)
What we need … (1) Classifier just like a clustering method
(one-versus-all incremental classifier)
(2) Clustering Method just like a Classifier(Metric Learning)
![Page 80: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/80.jpg)
one-versus-all incremental classifier
NotClass 1
NotClass 2
![Page 82: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/82.jpg)
Actually … You can also use deep neural network
to construct the metric learning staff
![Page 83: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/83.jpg)
Metric LearningAlways give me a whole new angle
to observe the world
![Page 84: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/84.jpg)
Remember that ... !Whatever you observe …
Whatever you draw !
![Page 85: PyData SF 2016 --- Moving forward through the darkness](https://reader031.fdocuments.net/reader031/viewer/2022022411/58ec96521a28ab9e628b46ad/html5/thumbnails/85.jpg)
Thanks for your attention!