SlideShare a Scribd company logo
CS 221: Artificial Intelligence Lecture 5: Machine Learning Peter Norvig and Sebastian Thrun
Outline ,[object Object],[object Object],[object Object],[object Object],[object Object]
Outline ,[object Object],[object Object],[object Object],[object Object],[object Object]
Machine Learning ,[object Object],[object Object],[object Object],[object Object],[object Object]
Machine Learning Lingo What? Parameters Structure Hidden concepts What from? Supervised Unsupervised Reinforcement Self-supervised What for? Prediction Diagnosis Compression Discovery How? Passive Active Online Offline Output? Classification Regression Clustering Details?? Generative Discriminative Smoothing
Supervised Machine Learning Given a training set: ( x 1 , y 1 ),  ( x 2 , y 2 ),  ( x 3 , y 3 ),  …   ( x n , y n ) Where each  y i   was generated by an unknown  y = f  ( x ), Discover a function  h  that approximates the true function  f.
Outline ,[object Object],[object Object],[object Object],[object Object],[object Object]
Classification Example: Spam Filter ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Dear Sir. First, I must solicit your confidence in this transaction, this is by virture of its nature as being utterly confidencial and top secret. … TO BE REMOVED FROM FUTURE MAILINGS, SIMPLY REPLY TO THIS MESSAGE AND PUT "REMOVE" IN THE SUBJECT. 99  MILLION EMAIL ADDRESSES FOR ONLY $99 Ok, Iknow this is blatantly OT but I'm beginning to go insane. Had an old Dell Dimension XPS sitting in the corner and decided to put it to use, I know it was working pre being stuck in the corner, but when I plugged it in, hit the power nothing happened.
A Spam Filter ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Dear Sir. First, I must solicit your confidence in this transaction, this is by virture of its nature as being utterly confidencial and top secret. … TO BE REMOVED FROM FUTURE MAILINGS, SIMPLY REPLY TO THIS MESSAGE AND PUT "REMOVE" IN THE SUBJECT. 99  MILLION EMAIL ADDRESSES FOR ONLY $99 Ok, Iknow this is blatantly OT but I'm beginning to go insane. Had an old Dell Dimension XPS sitting in the corner and decided to put it to use, I know it was working pre being stuck in the corner, but when I plugged it in, hit the power nothing happened.
Naïve Bayes for Text ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Word at position i, not i th  word in the dictionary!
General Naïve Bayes ,[object Object],[object Object],[object Object],[object Object],Y F 1 F n F 2 |Y| parameters n x |F| x |Y| parameters |Y| x |F| n  parameters
Example: Spam Filtering ,[object Object],[object Object],[object Object],the :  0.0156 to  :  0.0153 and :  0.0115 of  :  0.0095 you :  0.0093 a  :  0.0086 with:  0.0080 from:  0.0075 ... the :  0.0210 to  :  0.0133 of  :  0.0119 2002:  0.0110 with:  0.0108 from:  0.0107 and :  0.0105 a  :  0.0100 ... ham : 0.66 spam: 0.33 Counts from examples!
Spam Example P(spam | words) = e -76  / (e -76  + e -80.5 ) = 98.9% Word P(w|spam) P(w|ham) Tot Spam Tot Ham (prior) 0.33333 0.66666 -1.1 -0.4 Gary 0.00002 0.00021 -11.8 -8.9 would 0.00069 0.00084 -19.1 -16.0 you 0.00881 0.00304 -23.8 -21.8 like 0.00086 0.00083 -30.9 -28.9 to 0.01517 0.01339 -35.1 -33.2 lose 0.00008 0.00002 -44.5 -44.0 weight 0.00016 0.00002 -53.3 -55.0 while 0.00027 0.00027 -61.5 -63.2 you 0.00881 0.00304 -66.2 -69.0 sleep 0.00006 0.00001 -76.0 -80.5
Example: Overfitting ,[object Object],south-west : inf nation  : inf morally  : inf nicely  : inf extent  : inf seriously  : inf ... What went wrong here? screens  : inf minute  : inf guaranteed : inf $205.00  : inf delivery  : inf signature  : inf ...
Generalization and Overfitting ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Estimation: Smoothing ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],r g g
Estimation: Laplace Smoothing ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],H H T
Estimation: Linear Interpolation  ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Real NB: Smoothing ,[object Object],[object Object],helvetica : 11.4 seems  : 10.8 group  : 10.2 ago  :  8.4 areas  :  8.3 ... verdana : 28.8 Credit  : 28.4 ORDER  : 27.2 <FONT>  : 26.9 money  : 26.5 ... Do these make more sense?
Tuning on Held-Out Data ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
How to Learn ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Training Data Held-Out Data Test Data
What to Do About Errors? ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
A Digit Recognizer ,[object Object],[object Object]
Example: Digit Recognition ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],0 1 2 1 ??
Naïve Bayes for Digits ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Learning Model Parameters 1 0.1 2 0.1 3 0.1 4 0.1 5 0.1 6 0.1 7 0.1 8 0.1 9 0.1 0 0.1 1 0.01 2 0.05 3 0.05 4 0.30 5 0.80 6 0.90 7 0.05 8 0.60 9 0.50 0 0.80 1 0.05 2 0.01 3 0.90 4 0.80 5 0.90 6 0.90 7 0.25 8 0.85 9 0.60 0 0.80
Problem: Overfitting 2 wins!!
 
Outline ,[object Object],[object Object],[object Object],[object Object],[object Object]
Regression ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Regression: Minimizing Loss ,[object Object],[object Object]
Regression: Minimizing Loss
Regression: Minimizing Loss Choose weights to minimize sum of squared errors
Regression: Minimizing Loss
Regression: Minimizing Loss y  =  w 1   x  +  w 0 Linear algebra gives an exact solution to the minimization problem
Linear Algebra Solution
Don ’t Always Trust Linear Models
Regression by Gradient Descent w  =  any point   loop until convergence do: for each  w i  in  w  do: w i  = w i  – α  ∂  Loss ( w ) ∂  w i
Multivariate Regression ,[object Object],[object Object],[object Object],[object Object]
Overfitting ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Regularization and Sparsity L 1   regularization L 2   regularization ,[object Object]
Outline ,[object Object],[object Object],[object Object],[object Object],[object Object]
Linear Separator
Perceptron
Perceptron Algorithm ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
What Linear Separator to Pick?
What Linear Separator to Pick? Maximizes the “margin” Support Vector Machines
Non-Separable Data? ,[object Object],[object Object],[object Object],[object Object],X 1 X 2 X 3
Outline ,[object Object],[object Object],[object Object],[object Object],[object Object]
Nonparametric Models ,[object Object]
Nearest-Neighbor Classification ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Earthquakes and Explosions Using logistic regression (similar to linear regression) to do linear classification
K =1 Nearest Neighbors Using nearest neighbors to do classification
K =5 Nearest Neighbors Even with no parameters, you still have hyperparameters!
Curse of Dimensionality Average neighborhood size for 10-nearest neighbors,  n  dimensions, 1M uniform points
Curse of Dimensionality Proportion of points that are within the outer shell, 1% of thickness of the hypercube
Outline ,[object Object],[object Object],[object Object],[object Object],[object Object]
Machine Learning Lingo What? Parameters Structure Hidden concepts What from? Supervised Unsupervised Reinforcement Self-supervised What for? Prediction Diagnosis Compression Discovery How? Passive Active Online Offline Output? Classification Regression Clustering Details?? Generative Discriminative Smoothing

More Related Content

Viewers also liked

Tweets Classification using Naive Bayes and SVM
Tweets Classification using Naive Bayes and SVMTweets Classification using Naive Bayes and SVM
Tweets Classification using Naive Bayes and SVM
Trilok Sharma
 
Supervised Learning
Supervised LearningSupervised Learning
Supervised Learningbutest
 
Presentation on supervised learning
Presentation on supervised learningPresentation on supervised learning
Presentation on supervised learning
Tonmoy Bhagawati
 
A Reference Architecture for ETL 2.0
A Reference Architecture for ETL 2.0 A Reference Architecture for ETL 2.0
A Reference Architecture for ETL 2.0
DataWorks Summit
 
Hadoop and Enterprise Data Warehouse
Hadoop and Enterprise Data WarehouseHadoop and Enterprise Data Warehouse
Hadoop and Enterprise Data WarehouseDataWorks Summit
 
Taking Pnb To The Next Level
Taking Pnb To The Next LevelTaking Pnb To The Next Level
Taking Pnb To The Next Leveltiwari1989
 
Aemas newsletter december 2011 vol. 1 issue no. 2
Aemas newsletter december 2011 vol. 1 issue no. 2Aemas newsletter december 2011 vol. 1 issue no. 2
Aemas newsletter december 2011 vol. 1 issue no. 2
Niar El
 
BioengineeredTumorModel_DrJonasMoses_r2015
BioengineeredTumorModel_DrJonasMoses_r2015BioengineeredTumorModel_DrJonasMoses_r2015
BioengineeredTumorModel_DrJonasMoses_r2015Dr. Jonas Moses
 
凱絡媒體週報 2011 11 25
凱絡媒體週報 2011 11 25凱絡媒體週報 2011 11 25
凱絡媒體週報 2011 11 25Eson Chih
 
Marketing artikel factomagazine 1107 en 1108 (white space conflict)
Marketing artikel factomagazine 1107 en 1108 (white space conflict)Marketing artikel factomagazine 1107 en 1108 (white space conflict)
Marketing artikel factomagazine 1107 en 1108 (white space conflict)Mobiliteitsscan.com
 
Ren21 general
Ren21 generalRen21 general
Ren21 general
Shweta Koshy
 
Wil Group, Development Solutions in Africa
Wil Group, Development Solutions in AfricaWil Group, Development Solutions in Africa
Wil Group, Development Solutions in Africa
Ricky L. Stewart
 
Kennis rapportage blauw research_hnw_doe_je_zelf
Kennis rapportage blauw research_hnw_doe_je_zelfKennis rapportage blauw research_hnw_doe_je_zelf
Kennis rapportage blauw research_hnw_doe_je_zelfMobiliteitsscan.com
 
Cs221 lecture7-fall11
Cs221 lecture7-fall11Cs221 lecture7-fall11
Cs221 lecture7-fall11darwinrlo
 
Onderwijs in de steigers in Mago
Onderwijs in de steigers in MagoOnderwijs in de steigers in Mago
Onderwijs in de steigers in Mago
The Style Foundation
 

Viewers also liked (20)

Tweets Classification using Naive Bayes and SVM
Tweets Classification using Naive Bayes and SVMTweets Classification using Naive Bayes and SVM
Tweets Classification using Naive Bayes and SVM
 
Supervised Learning
Supervised LearningSupervised Learning
Supervised Learning
 
Presentation on supervised learning
Presentation on supervised learningPresentation on supervised learning
Presentation on supervised learning
 
A Reference Architecture for ETL 2.0
A Reference Architecture for ETL 2.0 A Reference Architecture for ETL 2.0
A Reference Architecture for ETL 2.0
 
Hadoop and Enterprise Data Warehouse
Hadoop and Enterprise Data WarehouseHadoop and Enterprise Data Warehouse
Hadoop and Enterprise Data Warehouse
 
Taking Pnb To The Next Level
Taking Pnb To The Next LevelTaking Pnb To The Next Level
Taking Pnb To The Next Level
 
Aemas newsletter december 2011 vol. 1 issue no. 2
Aemas newsletter december 2011 vol. 1 issue no. 2Aemas newsletter december 2011 vol. 1 issue no. 2
Aemas newsletter december 2011 vol. 1 issue no. 2
 
BioengineeredTumorModel_DrJonasMoses_r2015
BioengineeredTumorModel_DrJonasMoses_r2015BioengineeredTumorModel_DrJonasMoses_r2015
BioengineeredTumorModel_DrJonasMoses_r2015
 
Presentation2
Presentation2Presentation2
Presentation2
 
凱絡媒體週報 2011 11 25
凱絡媒體週報 2011 11 25凱絡媒體週報 2011 11 25
凱絡媒體週報 2011 11 25
 
The daily mail
The daily mailThe daily mail
The daily mail
 
Alm alloy
Alm alloyAlm alloy
Alm alloy
 
Marketing artikel factomagazine 1107 en 1108 (white space conflict)
Marketing artikel factomagazine 1107 en 1108 (white space conflict)Marketing artikel factomagazine 1107 en 1108 (white space conflict)
Marketing artikel factomagazine 1107 en 1108 (white space conflict)
 
Treball 11111
Treball 11111Treball 11111
Treball 11111
 
Ren21 general
Ren21 generalRen21 general
Ren21 general
 
Wil Group, Development Solutions in Africa
Wil Group, Development Solutions in AfricaWil Group, Development Solutions in Africa
Wil Group, Development Solutions in Africa
 
Kennis rapportage blauw research_hnw_doe_je_zelf
Kennis rapportage blauw research_hnw_doe_je_zelfKennis rapportage blauw research_hnw_doe_je_zelf
Kennis rapportage blauw research_hnw_doe_je_zelf
 
Cs221 lecture7-fall11
Cs221 lecture7-fall11Cs221 lecture7-fall11
Cs221 lecture7-fall11
 
 
Onderwijs in de steigers in Mago
Onderwijs in de steigers in MagoOnderwijs in de steigers in Mago
Onderwijs in de steigers in Mago
 

Similar to Cs221 lecture5-fall11

Supervised learning: Types of Machine Learning
Supervised learning: Types of Machine LearningSupervised learning: Types of Machine Learning
Supervised learning: Types of Machine Learning
Libya Thomas
 
Computational Biology, Part 4 Protein Coding Regions
Computational Biology, Part 4 Protein Coding RegionsComputational Biology, Part 4 Protein Coding Regions
Computational Biology, Part 4 Protein Coding Regionsbutest
 
Machine learning and_nlp
Machine learning and_nlpMachine learning and_nlp
Machine learning and_nlp
ankit_ppt
 
NaiveBayes.ppt
NaiveBayes.pptNaiveBayes.ppt
NaiveBayes.ppt
sabbirice08
 
NaiveBayes.ppt
NaiveBayes.pptNaiveBayes.ppt
NaiveBayes.ppt
CristopherAbalorio2
 
NaiveBayes.ppt
NaiveBayes.pptNaiveBayes.ppt
NaiveBayes.ppt
EslamAbdAlAziz4
 
An Introduction to boosting
An Introduction to boostingAn Introduction to boosting
An Introduction to boostingbutest
 
Explainable AI
Explainable AIExplainable AI
Explainable AI
Wagston Staehler
 
Data simulation basics
Data simulation basicsData simulation basics
Data simulation basics
Dorothy Bishop
 
Using binary classifiers
Using binary classifiersUsing binary classifiers
Using binary classifiersbutest
 
supervised.pptx
supervised.pptxsupervised.pptx
supervised.pptx
MohamedSaied316569
 
Anomaly detection Full Article
Anomaly detection Full ArticleAnomaly detection Full Article
Anomaly detection Full Article
MenglinLiu1
 
Explore ml day 2
Explore ml day 2Explore ml day 2
Explore ml day 2
preetikumara
 
4. Classification.pdf
4. Classification.pdf4. Classification.pdf
4. Classification.pdf
Jyoti Yadav
 
Supervised algorithms
Supervised algorithmsSupervised algorithms
Supervised algorithms
Yassine Akhiat
 
2013 - Andrei Zmievski: Machine learning para datos
2013 - Andrei Zmievski: Machine learning para datos2013 - Andrei Zmievski: Machine learning para datos
2013 - Andrei Zmievski: Machine learning para datos
PHP Conference Argentina
 
M08 BiasVarianceTradeoff
M08 BiasVarianceTradeoffM08 BiasVarianceTradeoff
M08 BiasVarianceTradeoff
Raman Kannan
 
06-01 Machine Learning and Linear Regression.pptx
06-01 Machine Learning and Linear Regression.pptx06-01 Machine Learning and Linear Regression.pptx
06-01 Machine Learning and Linear Regression.pptx
SaharA84
 
Model Selection and Validation
Model Selection and ValidationModel Selection and Validation
Model Selection and Validation
gmorishita
 

Similar to Cs221 lecture5-fall11 (20)

Supervised learning: Types of Machine Learning
Supervised learning: Types of Machine LearningSupervised learning: Types of Machine Learning
Supervised learning: Types of Machine Learning
 
Computational Biology, Part 4 Protein Coding Regions
Computational Biology, Part 4 Protein Coding RegionsComputational Biology, Part 4 Protein Coding Regions
Computational Biology, Part 4 Protein Coding Regions
 
Machine learning and_nlp
Machine learning and_nlpMachine learning and_nlp
Machine learning and_nlp
 
NaiveBayes.ppt
NaiveBayes.pptNaiveBayes.ppt
NaiveBayes.ppt
 
NaiveBayes.ppt
NaiveBayes.pptNaiveBayes.ppt
NaiveBayes.ppt
 
NaiveBayes.ppt
NaiveBayes.pptNaiveBayes.ppt
NaiveBayes.ppt
 
Classification
ClassificationClassification
Classification
 
An Introduction to boosting
An Introduction to boostingAn Introduction to boosting
An Introduction to boosting
 
Explainable AI
Explainable AIExplainable AI
Explainable AI
 
Data simulation basics
Data simulation basicsData simulation basics
Data simulation basics
 
Using binary classifiers
Using binary classifiersUsing binary classifiers
Using binary classifiers
 
supervised.pptx
supervised.pptxsupervised.pptx
supervised.pptx
 
Anomaly detection Full Article
Anomaly detection Full ArticleAnomaly detection Full Article
Anomaly detection Full Article
 
Explore ml day 2
Explore ml day 2Explore ml day 2
Explore ml day 2
 
4. Classification.pdf
4. Classification.pdf4. Classification.pdf
4. Classification.pdf
 
Supervised algorithms
Supervised algorithmsSupervised algorithms
Supervised algorithms
 
2013 - Andrei Zmievski: Machine learning para datos
2013 - Andrei Zmievski: Machine learning para datos2013 - Andrei Zmievski: Machine learning para datos
2013 - Andrei Zmievski: Machine learning para datos
 
M08 BiasVarianceTradeoff
M08 BiasVarianceTradeoffM08 BiasVarianceTradeoff
M08 BiasVarianceTradeoff
 
06-01 Machine Learning and Linear Regression.pptx
06-01 Machine Learning and Linear Regression.pptx06-01 Machine Learning and Linear Regression.pptx
06-01 Machine Learning and Linear Regression.pptx
 
Model Selection and Validation
Model Selection and ValidationModel Selection and Validation
Model Selection and Validation
 

More from darwinrlo

Cs221 probability theory
Cs221 probability theoryCs221 probability theory
Cs221 probability theorydarwinrlo
 
Cs221 logic-planning
Cs221 logic-planningCs221 logic-planning
Cs221 logic-planningdarwinrlo
 
Cs221 linear algebra
Cs221 linear algebraCs221 linear algebra
Cs221 linear algebradarwinrlo
 
Cs221 lecture8-fall11
Cs221 lecture8-fall11Cs221 lecture8-fall11
Cs221 lecture8-fall11darwinrlo
 
Cs221 lecture6-fall11
Cs221 lecture6-fall11Cs221 lecture6-fall11
Cs221 lecture6-fall11darwinrlo
 
Cs221 lecture4-fall11
Cs221 lecture4-fall11Cs221 lecture4-fall11
Cs221 lecture4-fall11darwinrlo
 
Cs221 lecture3-fall11
Cs221 lecture3-fall11Cs221 lecture3-fall11
Cs221 lecture3-fall11darwinrlo
 

More from darwinrlo (8)

Cs221 probability theory
Cs221 probability theoryCs221 probability theory
Cs221 probability theory
 
Cs221 logic-planning
Cs221 logic-planningCs221 logic-planning
Cs221 logic-planning
 
Cs221 linear algebra
Cs221 linear algebraCs221 linear algebra
Cs221 linear algebra
 
Cs221 lecture8-fall11
Cs221 lecture8-fall11Cs221 lecture8-fall11
Cs221 lecture8-fall11
 
Cs221 lecture6-fall11
Cs221 lecture6-fall11Cs221 lecture6-fall11
Cs221 lecture6-fall11
 
Cs221 lecture4-fall11
Cs221 lecture4-fall11Cs221 lecture4-fall11
Cs221 lecture4-fall11
 
Cs221 lecture3-fall11
Cs221 lecture3-fall11Cs221 lecture3-fall11
Cs221 lecture3-fall11
 
Cs221 rl
Cs221 rlCs221 rl
Cs221 rl
 

Recently uploaded

The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
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
 
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
Peter Spielvogel
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
James Anderson
 
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
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
Kari Kakkonen
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
James Anderson
 
Introduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - CybersecurityIntroduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - Cybersecurity
mikeeftimakis1
 
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
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
Pierluigi Pugliese
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
Neo4j
 
UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5
DianaGray10
 
20240607 QFM018 Elixir Reading List May 2024
20240607 QFM018 Elixir Reading List May 202420240607 QFM018 Elixir Reading List May 2024
20240607 QFM018 Elixir Reading List May 2024
Matthew Sinclair
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Paige Cruz
 
Pushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 daysPushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 days
Adtran
 
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
Neo4j
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
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)

The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
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...
 
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
 
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
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
 
Introduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - CybersecurityIntroduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - Cybersecurity
 
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...
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
 
UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5
 
20240607 QFM018 Elixir Reading List May 2024
20240607 QFM018 Elixir Reading List May 202420240607 QFM018 Elixir Reading List May 2024
20240607 QFM018 Elixir Reading List May 2024
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
 
Pushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 daysPushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 days
 
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
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)
 

Cs221 lecture5-fall11

  • 1. CS 221: Artificial Intelligence Lecture 5: Machine Learning Peter Norvig and Sebastian Thrun
  • 2.
  • 3.
  • 4.
  • 5. Machine Learning Lingo What? Parameters Structure Hidden concepts What from? Supervised Unsupervised Reinforcement Self-supervised What for? Prediction Diagnosis Compression Discovery How? Passive Active Online Offline Output? Classification Regression Clustering Details?? Generative Discriminative Smoothing
  • 6. Supervised Machine Learning Given a training set: ( x 1 , y 1 ), ( x 2 , y 2 ), ( x 3 , y 3 ), … ( x n , y n ) Where each y i was generated by an unknown y = f ( x ), Discover a function h that approximates the true function f.
  • 7.
  • 8.
  • 9.
  • 10.
  • 11.
  • 12.
  • 13. Spam Example P(spam | words) = e -76 / (e -76 + e -80.5 ) = 98.9% Word P(w|spam) P(w|ham) Tot Spam Tot Ham (prior) 0.33333 0.66666 -1.1 -0.4 Gary 0.00002 0.00021 -11.8 -8.9 would 0.00069 0.00084 -19.1 -16.0 you 0.00881 0.00304 -23.8 -21.8 like 0.00086 0.00083 -30.9 -28.9 to 0.01517 0.01339 -35.1 -33.2 lose 0.00008 0.00002 -44.5 -44.0 weight 0.00016 0.00002 -53.3 -55.0 while 0.00027 0.00027 -61.5 -63.2 you 0.00881 0.00304 -66.2 -69.0 sleep 0.00006 0.00001 -76.0 -80.5
  • 14.
  • 15.
  • 16.
  • 17.
  • 18.
  • 19.
  • 20.
  • 21.
  • 22.
  • 23.
  • 24.
  • 25.
  • 26. Learning Model Parameters 1 0.1 2 0.1 3 0.1 4 0.1 5 0.1 6 0.1 7 0.1 8 0.1 9 0.1 0 0.1 1 0.01 2 0.05 3 0.05 4 0.30 5 0.80 6 0.90 7 0.05 8 0.60 9 0.50 0 0.80 1 0.05 2 0.01 3 0.90 4 0.80 5 0.90 6 0.90 7 0.25 8 0.85 9 0.60 0 0.80
  • 28.  
  • 29.
  • 30.
  • 31.
  • 33. Regression: Minimizing Loss Choose weights to minimize sum of squared errors
  • 35. Regression: Minimizing Loss y = w 1 x + w 0 Linear algebra gives an exact solution to the minimization problem
  • 37. Don ’t Always Trust Linear Models
  • 38. Regression by Gradient Descent w = any point loop until convergence do: for each w i in w do: w i = w i – α ∂ Loss ( w ) ∂ w i
  • 39.
  • 40.
  • 41.
  • 42.
  • 45.
  • 47. What Linear Separator to Pick? Maximizes the “margin” Support Vector Machines
  • 48.
  • 49.
  • 50.
  • 51.
  • 52. Earthquakes and Explosions Using logistic regression (similar to linear regression) to do linear classification
  • 53. K =1 Nearest Neighbors Using nearest neighbors to do classification
  • 54. K =5 Nearest Neighbors Even with no parameters, you still have hyperparameters!
  • 55. Curse of Dimensionality Average neighborhood size for 10-nearest neighbors, n dimensions, 1M uniform points
  • 56. Curse of Dimensionality Proportion of points that are within the outer shell, 1% of thickness of the hypercube
  • 57.
  • 58. Machine Learning Lingo What? Parameters Structure Hidden concepts What from? Supervised Unsupervised Reinforcement Self-supervised What for? Prediction Diagnosis Compression Discovery How? Passive Active Online Offline Output? Classification Regression Clustering Details?? Generative Discriminative Smoothing