SlideShare ist ein Scribd-Unternehmen logo
1 von 55
Downloaden Sie, um offline zu lesen
Practical Data Science
An Introduction to Supervised Machine Learning
and Pattern Classiļ¬cation: The Big Picture
Michigan State University
NextGen Bioinformatics Seminars - 2015
Sebastian Raschka
Feb. 11, 2015
A Little Bit About Myself ...
Developing software & methods for
- Protein ligand docking
- Large scale drug/inhibitor discovery
PhD candidate in Dr. L. Kuhnā€™s Lab:
and some other machine learning side-projects ā€¦
What is Machine Learning?
http://drewconway.com/zia/2013/3/26/the-data-science-venn-diagram
"Field of study that gives computers the
ability to learn without being explicitly
programmed.ā€
(Arthur Samuel, 1959)
By Phillip Taylor [CC BY 2.0]
http://commons.wikimedia.org/wiki/
File:American_book_company_1916._letter_envelope-2.JPG#ļ¬lelinks
[public domain]
https://ļ¬‚ic.kr/p/5BLW6G [CC BY 2.0]
Text Recognition
Spam Filtering
Biology
Examples of Machine Learning
Examples of Machine Learning
http://googleresearch.blogspot.com/2014/11/a-picture-is-worth-thousand-coherent.html
By Steve Jurvetson [CC BY 2.0]
Self-driving cars
Photo search
and many, many
more ...
Recommendation systems
http://commons.wikimedia.org/wiki/File:Netļ¬‚ix_logo.svg [public domain]
How many of you have used
machine learning before?
Our Agenda
ā€¢ Concepts and the big picture
ā€¢ Workļ¬‚ow
ā€¢ Practical tips & good habits
Learning
ā€¢ Labeled data
ā€¢ Direct feedback
ā€¢ Predict outcome/future
ā€¢ Decision process
ā€¢ Reward system
ā€¢ Learn series of actions
ā€¢ No labels
ā€¢ No feedback
ā€¢ ā€œFind hidden structureā€
Unsupervised
Supervised
Reinforcement
Unsupervised
learning
Supervised
learning
Clustering:
[DBSCAN on a toy dataset]
Classiļ¬cation:
[SVM on 2 classes of the Wine dataset]
Regression:
[Soccer Fantasy Score prediction]
Todayā€™s topic
Supervised LearningUnsupervised Learning
Instances (samples, observations)
Features (attributes, dimensions) Classes (targets)
Nomenclature
sepal_length sepal_width petal_length petal_width class
1 5.1 3.5 1.4 0.2 setosa
2 4.9 3.0 1.4 0.2 setosa
ā€¦ ā€¦ ā€¦ ā€¦ ā€¦ ā€¦
50 6.4 3.2 4.5 1.5 veriscolor
ā€¦ ā€¦ ā€¦ ā€¦ ā€¦ ā€¦
150 5.9 3.0 5.1 1.8 virginica
https://archive.ics.uci.edu/ml/datasets/Iris
IRIS
Classiļ¬cation
x1
x2
class1
class2
1) Learn from training data
2) Map unseen (new) data
?
Feature Extraction
Feature Selection
Dimensionality Reduction
Feature Scaling
Raw Data Collection
Pre-Processing
Sampling
Test Dataset
Training Dataset
Learning Algorithm
Training
Post-Processing
Cross Validation
Final Classiļ¬cation/
Regression Model
New DataPre-Processing
Reļ¬nement
Prediction
Split
Supervised
Learning
Sebastian Raschka 2014
Missing Data
Performance Metrics
Model Selection
Hyperparameter
Optimization
This work is licensed under a Creative Commons Attribution 4.0 International License.
Final Model
Evaluation
Feature Extraction
Feature Selection
Dimensionality Reduction
Feature Scaling
Raw Data Collection
Pre-Processing
Sampling
Test Dataset
Training Dataset
Learning Algorithm
Training
Post-Processing
Cross Validation
Final Classiļ¬cation/
Regression Model
New DataPre-Processing
Reļ¬nement
Prediction
Split
Supervised
Learning
Sebastian Raschka 2014
Missing Data
Performance Metrics
Model Selection
Hyperparameter
Optimization
This work is licensed under a Creative Commons Attribution 4.0 International License.
Final Model
Evaluation
A Few Common Classiļ¬ers
Decision Tree
Perceptron Naive Bayes
Ensemble Methods: Random Forest, Bagging, AdaBoost
Support Vector Machine
K-Nearest Neighbor
Logistic Regression
Artiļ¬cial Neural Network / Deep Learning
Discriminative Algorithms
Generative Algorithms
ā€¢ Models a more general problem: how the data was generated.
ā€¢ I.e., the distribution of the class; joint probability distribution p(x,y).
ā€¢ Naive Bayes, Bayesian Belief Network classiļ¬er, Restricted
Boltzmann Machine ā€¦
ā€¢ Map x ā†’ y directly.
ā€¢ E.g., distinguish between people speaking different languages
without learning the languages.
ā€¢ Logistic Regression, SVM, Neural Networks ā€¦
Examples of Discriminative Classiļ¬ers:
Perceptron
xi1
xi2
w1
w2
Ī£ yi
y = wTx = w0 + w1x1 + w2x2
1
F. Rosenblatt. The perceptron, a perceiving and recognizing automaton Project Para. Cornell Aeronautical Laboratory, 1957.
x1
x2
y āˆˆ {-1,1}
w0
wj = weight
xi = training sample
yi = desired output
yi = actual output
t = iteration step
Ī· = learning rate
Īø = threshold (here 0)
update rule:
wj(t+1) = wj(t) + Ī·(yi - yi)xi
1 if wTxi ā‰„ Īø
-1 otherwise
^
^
^
^
yi
^
until
t+1 = max iter
or error = 0
Discriminative Classiļ¬ers:
Perceptron
F. Rosenblatt. The perceptron, a perceiving and recognizing automaton Project Para. Cornell Aeronautical Laboratory, 1957.
- Binary classiļ¬er (one vs all, OVA)
- Convergence problems (set n iterations)
- Modiļ¬cation: stochastic gradient descent
- ā€œModernā€ perceptron: Support Vector Machine (maximize margin)
- Multilayer perceptron (MLP)
xi1
xi2
w1
w2
Ī£ yi
1
y āˆˆ {-1,1}
w0
^
x1
x2
Generative Classiļ¬ers:
Naive Bayes
Bayes Theorem: P(Ļ‰j | xi) =
P(xi | Ļ‰j) P(Ļ‰j)
P(xi)
Posterior probability =
Likelihood x Prior probability
Evidence
Iris example: P(ā€œSetosa"| xi), xi = [4.5 cm, 7.4 cm]
Generative Classiļ¬ers:
Naive Bayes
Decision Rule:
Bayes Theorem: P(Ļ‰j | xi) =
P(xi | Ļ‰j) P(Ļ‰j)
P(xi)
pred. class label Ļ‰j argmax P(Ļ‰j | xi)
i = 1, ā€¦, m
e.g., j āˆˆ {Setosa, Versicolor, Virginica}
Class-conditional
probability
(here Gaussian kernel):
Generative Classiļ¬ers:
Naive Bayes
Prior probability:
Evidence:
(cancels out)
(class frequency)
P(Ļ‰j | xi) =
P(xi | Ļ‰j) P(Ļ‰j)
P(xi)
P(Ļ‰j) =
NĻ‰j
Nc
P(xik |Ļ‰j) =
1
āˆš (2 Ļ€ ĻƒĻ‰j
2)
exp
( )-
(xik - Ī¼Ļ‰j)2
2ĻƒĻ‰j
2
P(xi |Ļ‰j) P(xik |Ļ‰j)
Generative Classiļ¬ers:
Naive Bayes
- Naive conditional independence assumption typically
violated
- Works well for small datasets
- Multinomial model still quite popular for text classiļ¬cation
(e.g., spam ļ¬lter)
Non-Parametric Classiļ¬ers:
K-Nearest Neighbor
- Simple!
- Lazy learner
- Very susceptible to curse of dimensionality
k=3
e.g., k=1
Iris Example
Setosa Virginica Versicolor
k = 3
mahalanobis dist.
uniform weights
C = 3
depth = 2
Decision Tree
Entropy =
depth = 4
petal length <= 2.45?
petal length <= 4.75?
Setosa
Virginica Versicolor
Yes No
e.g., 2 (- 0.5 log2(0.5)) = 1
āˆ‘āˆ’pi logk pi
i
Information Gain =
entropy(parent) ā€“ [avg entropy(children)]
NoYes
depth = 2
"No Free Lunch" :(
Roughly speaking:
ā€œNo one model works best for all possible situations.ā€
Our model is a simpliļ¬cation of reality
Simpliļ¬cation is based on assumptions (model bias)
Assumptions fail in certain situations
D. H. Wolpert. The supervised learning no-free-lunch theorems. In Soft Computing and Industry, pages 25ā€“42. Springer, 2002.
Which Algorithm?
ā€¢ What is the size and dimensionality of my training set?
ā€¢ Is the data linearly separable?
ā€¢ How much do I care about computational efļ¬ciency?
- Model building vs. real-time prediction time
- Eager vs. lazy learning / on-line vs. batch learning
- prediction performance vs. speed
ā€¢ Do I care about interpretability or should it "just work well?"
ā€¢ ...
Feature Extraction
Feature Selection
Dimensionality Reduction
Feature Scaling
Raw Data Collection
Pre-Processing
Sampling
Test Dataset
Training Dataset
Learning Algorithm
Training
Post-Processing
Cross Validation
Final Classiļ¬cation/
Regression Model
New DataPre-Processing
Reļ¬nement
Prediction
Split
Supervised
Learning
Sebastian Raschka 2014
Missing Data
Performance Metrics
Model Selection
Hyperparameter
Optimization
This work is licensed under a Creative Commons Attribution 4.0 International License.
Final Model
Evaluation
Missing Values:
- Remove features (columns)
- Remove samples (rows)
- Imputation (mean, nearest neighbor, ā€¦)
Sampling:
- Random split into training and validation sets
- Typically 60/40, 70/30, 80/20
- Donā€™t use validation set until the very end! (overļ¬tting)
Feature Scaling:
e.g., standardization:
- Faster convergence (gradient descent)
- Distances on same scale (k-NN with Euclidean distance)
- Mean centering for free
- Normal distributed data
- Numerical stability by avoiding small weights
z =
xik - Ī¼k
Ļƒk
(use same parameters for the test/new data!)
Categorical Variables
color size prize class
label
0 green M 10.1 class1
1 red L 13.5 class2
2 blue XL 15.3 class1
ordinalnominal
green ā†’ (1,0,0)
red ā†’ (0,1,0)
blue ā†’ (0,0,1)
class
label
color=blue color=green color=red prize size
0 0 0 1 0 10.1 1
1 1 0 0 1 13.5 2
2 0 1 0 0 15.3 3
M ā†’ 1
L ā†’ 2
XL ā†’ 3
Feature Extraction
Feature Selection
Dimensionality Reduction
Feature Scaling
Raw Data Collection
Pre-Processing
Sampling
Test Dataset
Training Dataset
Learning Algorithm
Training
Post-Processing
Cross Validation
Final Classiļ¬cation/
Regression Model
New DataPre-Processing
Reļ¬nement
Prediction
Split
Supervised
Learning
Sebastian Raschka 2014
Missing Data
Performance Metrics
Model Selection
Hyperparameter
Optimization
This work is licensed under a Creative Commons Attribution 4.0 International License.
Final Model
Evaluation
Generalization Error and Overļ¬tting
How well does the model perform on unseen data?
Generalization Error and Overļ¬tting
Error Metrics: Confusion Matrix
TP
[Linear SVM on sepal/petal lengths]
TN
FN
FP
here: ā€œsetosaā€ = ā€œpositiveā€
Error Metrics
TP
[Linear SVM on sepal/petal lengths]
TN
FN
FP
here: ā€œsetosaā€ = ā€œpositiveā€
TP + TN
FP +FN +TP +TN
Accuracy =
= 1 - Error
FP
N
TP
P
False Positive Rate =
TP
TP + FP
Precision =
True Positive Rate =
(Recall)
ā€œmicroā€ and ā€œmacroā€
averaging for multi-class
Receiver Operating Characteristic
(ROC) Curves
Test set
Training dataset Test dataset
Complete dataset
Test set
Test set
Test set
1st iteration calc. error
calc. error
calc. error
calc. error
calculate
avg. error
k-fold cross-validation (k=4):
2nd iteration
3rd iteration
4th iteration
fold 1 fold 2 fold 3 fold 4
Model Selection
k-fold CV and ROC
Feature Selection
- Domain knowledge
- Variance threshold
- Exhaustive search
- Decision trees
- ā€¦
IMPORTANT!
(Noise, overļ¬tting, curse of dimensionality, efļ¬ciency)
X = [x1, x2, x3, x4]start:
stop:
(if d = k)
X = [x1, x3, x4]
X = [x1, x3]
Simplest example:
Greedy Backward Selection
Dimensionality Reduction
ā€¢ Transformation onto a new feature subspace
ā€¢ e.g., Principal Component Analysis (PCA)
ā€¢ Find directions of maximum variance
ā€¢ Retain most of the information
0. Standardize data
1. Compute covariance matrix
z =
xik - Ī¼k
Ļƒik = āˆ‘ (xij - Āµj) (xik - Āµk)
Ļƒk
1
in -1
Ļƒ2
1 Ļƒ12 Ļƒ13 Ļƒ14
Ļƒ21 Ļƒ2
2 Ļƒ23 Ļƒ24
Ļƒ31 Ļƒ32 Ļƒ2
3 Ļƒ34
Ļƒ41 Ļƒ42 Ļƒ43 Ļƒ2
4
āˆ‘ =
PCA in 3 Steps
2. Eigendecomposition and sorting eigenvalues
PCA in 3 Steps
X v = Ī» v
Eigenvectors
[[ 0.52237162 -0.37231836 -0.72101681 0.26199559]
[-0.26335492 -0.92555649 0.24203288 -0.12413481]
[ 0.58125401 -0.02109478 0.14089226 -0.80115427]
[ 0.56561105 -0.06541577 0.6338014 0.52354627]]
Eigenvalues
[ 2.93035378 0.92740362 0.14834223 0.02074601]
(from high to low)
3. Select top k eigenvectors and transform data
PCA in 3 Steps
Eigenvectors
[[ 0.52237162 -0.37231836 -0.72101681 0.26199559]
[-0.26335492 -0.92555649 0.24203288 -0.12413481]
[ 0.58125401 -0.02109478 0.14089226 -0.80115427]
[ 0.56561105 -0.06541577 0.6338014 0.52354627]]
Eigenvalues
[ 2.93035378 0.92740362 0.14834223 0.02074601]
[First 2 PCs of Iris]
Hyperparameter Optimization:
GridSearch in scikit-learn
Non-Linear Problems
- XOR gate
k=11
uniform weights
C=1
C=1000,
gamma=0.1
depth=4
Kernel Trick
Kernel function
Kernel
Map onto high-dimensional space (non-linear combinations)
Kernel Trick
Trick: No explicit dot product!
Radius Basis Function (RBF) Kernel:
Kernel PCA
PC1, linear PCA PC1, kernel PCA
Feature Extraction
Feature Selection
Dimensionality Reduction
Feature Scaling
Raw Data Collection
Pre-Processing
Sampling
Test Dataset
Training Dataset
Learning Algorithm
Training
Post-Processing
Cross Validation
Final Classiļ¬cation/
Regression Model
New DataPre-Processing
Reļ¬nement
Prediction
Split
Supervised
Learning
Sebastian Raschka 2014
Missing Data
Performance Metrics
Model Selection
Hyperparameter
Optimization
This work is licensed under a Creative Commons Attribution 4.0 International License.
Final Model
Evaluation
Questions?
mail@sebastianraschka.com
https://github.com/rasbt
@rasbt
Thanks!
Additional Slides
Inspiring Literature
P. N. Klein. Coding the Matrix: Linear
Algebra Through Computer Science
Applications. Newtonian Press, 2013.
R. Schutt and C. Oā€™Neil. Doing Data
Science: Straight Talk from the Frontline.
Oā€™Reilly Media, Inc., 2013.
S. Gutierrez. Data Scientists at Work.
Apress, 2014.
R. O. Duda, P. E. Hart, and D. G. Stork.
Pattern classiļ¬cation. 2nd. Edition. New
York, 2001.
Useful Online Resources
https://www.coursera.org/course/ml
http://stats.stackexchange.com
http://www.kaggle.com
My Favorite Tools
http://stanford.edu/~mwaskom/software/seaborn/
Seaborn
http://www.numpy.org
http://pandas.pydata.org
http://scikit-learn.org/stable/
http://ipython.org/notebook.html
class1
class2
Which one to pick?
class1
class2
The problem of overļ¬tting
Generalization error!

Weitere Ƥhnliche Inhalte

Was ist angesagt?

supervised learning
supervised learningsupervised learning
supervised learningAmar Tripathi
Ā 
Machine Learning with Decision trees
Machine Learning with Decision treesMachine Learning with Decision trees
Machine Learning with Decision treesKnoldus Inc.
Ā 
Introduction to Linear Discriminant Analysis
Introduction to Linear Discriminant AnalysisIntroduction to Linear Discriminant Analysis
Introduction to Linear Discriminant AnalysisJaclyn Kokx
Ā 
boosting algorithm
boosting algorithmboosting algorithm
boosting algorithmPrithvi Paneru
Ā 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual IntroductionLukas Masuch
Ā 
Lecture 18: Gaussian Mixture Models and Expectation Maximization
Lecture 18: Gaussian Mixture Models and Expectation MaximizationLecture 18: Gaussian Mixture Models and Expectation Maximization
Lecture 18: Gaussian Mixture Models and Expectation Maximizationbutest
Ā 
Deep Dive into Hyperparameter Tuning
Deep Dive into Hyperparameter TuningDeep Dive into Hyperparameter Tuning
Deep Dive into Hyperparameter TuningShubhmay Potdar
Ā 
Linear discriminant analysis
Linear discriminant analysisLinear discriminant analysis
Linear discriminant analysisBangalore
Ā 
Introduction to Machine Learning Classifiers
Introduction to Machine Learning ClassifiersIntroduction to Machine Learning Classifiers
Introduction to Machine Learning ClassifiersFunctional Imperative
Ā 
Decision tree and random forest
Decision tree and random forestDecision tree and random forest
Decision tree and random forestLippo Group Digital
Ā 
Confusion Matrix
Confusion MatrixConfusion Matrix
Confusion MatrixRajat Gupta
Ā 
NAIVE BAYES CLASSIFIER
NAIVE BAYES CLASSIFIERNAIVE BAYES CLASSIFIER
NAIVE BAYES CLASSIFIERKnoldus Inc.
Ā 
K - Nearest neighbor ( KNN )
K - Nearest neighbor  ( KNN )K - Nearest neighbor  ( KNN )
K - Nearest neighbor ( KNN )Mohammad Junaid Khan
Ā 
Ensemble learning
Ensemble learningEnsemble learning
Ensemble learningHaris Jamil
Ā 
Machine Learning With Logistic Regression
Machine Learning  With Logistic RegressionMachine Learning  With Logistic Regression
Machine Learning With Logistic RegressionKnoldus Inc.
Ā 
Basics of Machine Learning
Basics of Machine LearningBasics of Machine Learning
Basics of Machine Learningbutest
Ā 
Training Neural Networks
Training Neural NetworksTraining Neural Networks
Training Neural NetworksDatabricks
Ā 
Pattern Recognition
Pattern RecognitionPattern Recognition
Pattern RecognitionTalal Alsubaie
Ā 

Was ist angesagt? (20)

supervised learning
supervised learningsupervised learning
supervised learning
Ā 
Clustering
ClusteringClustering
Clustering
Ā 
Machine Learning with Decision trees
Machine Learning with Decision treesMachine Learning with Decision trees
Machine Learning with Decision trees
Ā 
Introduction to Linear Discriminant Analysis
Introduction to Linear Discriminant AnalysisIntroduction to Linear Discriminant Analysis
Introduction to Linear Discriminant Analysis
Ā 
boosting algorithm
boosting algorithmboosting algorithm
boosting algorithm
Ā 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual Introduction
Ā 
Lecture 18: Gaussian Mixture Models and Expectation Maximization
Lecture 18: Gaussian Mixture Models and Expectation MaximizationLecture 18: Gaussian Mixture Models and Expectation Maximization
Lecture 18: Gaussian Mixture Models and Expectation Maximization
Ā 
Deep Dive into Hyperparameter Tuning
Deep Dive into Hyperparameter TuningDeep Dive into Hyperparameter Tuning
Deep Dive into Hyperparameter Tuning
Ā 
Linear discriminant analysis
Linear discriminant analysisLinear discriminant analysis
Linear discriminant analysis
Ā 
Introduction to Machine Learning Classifiers
Introduction to Machine Learning ClassifiersIntroduction to Machine Learning Classifiers
Introduction to Machine Learning Classifiers
Ā 
Decision tree and random forest
Decision tree and random forestDecision tree and random forest
Decision tree and random forest
Ā 
Confusion Matrix
Confusion MatrixConfusion Matrix
Confusion Matrix
Ā 
NAIVE BAYES CLASSIFIER
NAIVE BAYES CLASSIFIERNAIVE BAYES CLASSIFIER
NAIVE BAYES CLASSIFIER
Ā 
K - Nearest neighbor ( KNN )
K - Nearest neighbor  ( KNN )K - Nearest neighbor  ( KNN )
K - Nearest neighbor ( KNN )
Ā 
Ensemble learning
Ensemble learningEnsemble learning
Ensemble learning
Ā 
Machine Learning
Machine LearningMachine Learning
Machine Learning
Ā 
Machine Learning With Logistic Regression
Machine Learning  With Logistic RegressionMachine Learning  With Logistic Regression
Machine Learning With Logistic Regression
Ā 
Basics of Machine Learning
Basics of Machine LearningBasics of Machine Learning
Basics of Machine Learning
Ā 
Training Neural Networks
Training Neural NetworksTraining Neural Networks
Training Neural Networks
Ā 
Pattern Recognition
Pattern RecognitionPattern Recognition
Pattern Recognition
Ā 

Andere mochten auch

Tutorial on Deep learning and Applications
Tutorial on Deep learning and ApplicationsTutorial on Deep learning and Applications
Tutorial on Deep learning and ApplicationsNhatHai Phan
Ā 
Introduction to Big Data/Machine Learning
Introduction to Big Data/Machine LearningIntroduction to Big Data/Machine Learning
Introduction to Big Data/Machine LearningLars Marius Garshol
Ā 
Artificial neural network
Artificial neural networkArtificial neural network
Artificial neural networkDEEPASHRI HK
Ā 
Hadoop and Machine Learning
Hadoop and Machine LearningHadoop and Machine Learning
Hadoop and Machine Learningjoshwills
Ā 
How to Interview a Data Scientist
How to Interview a Data ScientistHow to Interview a Data Scientist
How to Interview a Data ScientistDaniel Tunkelang
Ā 
Data By The People, For The People
Data By The People, For The PeopleData By The People, For The People
Data By The People, For The PeopleDaniel Tunkelang
Ā 
A Statistician's View on Big Data and Data Science (Version 1)
A Statistician's View on Big Data and Data Science (Version 1)A Statistician's View on Big Data and Data Science (Version 1)
A Statistician's View on Big Data and Data Science (Version 1)Prof. Dr. Diego Kuonen
Ā 
Hands-on Deep Learning in Python
Hands-on Deep Learning in PythonHands-on Deep Learning in Python
Hands-on Deep Learning in PythonImry Kissos
Ā 
10 Lessons Learned from Building Machine Learning Systems
10 Lessons Learned from Building Machine Learning Systems10 Lessons Learned from Building Machine Learning Systems
10 Lessons Learned from Building Machine Learning SystemsXavier Amatriain
Ā 
Big Data [sorry] & Data Science: What Does a Data Scientist Do?
Big Data [sorry] & Data Science: What Does a Data Scientist Do?Big Data [sorry] & Data Science: What Does a Data Scientist Do?
Big Data [sorry] & Data Science: What Does a Data Scientist Do?Data Science London
Ā 
How to Become a Data Scientist
How to Become a Data ScientistHow to Become a Data Scientist
How to Become a Data Scientistryanorban
Ā 
A tutorial on deep learning at icml 2013
A tutorial on deep learning at icml 2013A tutorial on deep learning at icml 2013
A tutorial on deep learning at icml 2013Philip Zheng
Ā 
Introduction to Mahout and Machine Learning
Introduction to Mahout and Machine LearningIntroduction to Mahout and Machine Learning
Introduction to Mahout and Machine LearningVarad Meru
Ā 
Deep Learning for Natural Language Processing
Deep Learning for Natural Language ProcessingDeep Learning for Natural Language Processing
Deep Learning for Natural Language ProcessingDevashish Shanker
Ā 
Machine Learning and Data Mining: 12 Classification Rules
Machine Learning and Data Mining: 12 Classification RulesMachine Learning and Data Mining: 12 Classification Rules
Machine Learning and Data Mining: 12 Classification RulesPier Luca Lanzi
Ā 
Myths and Mathemagical Superpowers of Data Scientists
Myths and Mathemagical Superpowers of Data ScientistsMyths and Mathemagical Superpowers of Data Scientists
Myths and Mathemagical Superpowers of Data ScientistsDavid Pittman
Ā 
Tips for data science competitions
Tips for data science competitionsTips for data science competitions
Tips for data science competitionsOwen Zhang
Ā 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networksSi Haem
Ā 
10 R Packages to Win Kaggle Competitions
10 R Packages to Win Kaggle Competitions10 R Packages to Win Kaggle Competitions
10 R Packages to Win Kaggle CompetitionsDataRobot
Ā 
Artificial Intelligence Presentation
Artificial Intelligence PresentationArtificial Intelligence Presentation
Artificial Intelligence Presentationlpaviglianiti
Ā 

Andere mochten auch (20)

Tutorial on Deep learning and Applications
Tutorial on Deep learning and ApplicationsTutorial on Deep learning and Applications
Tutorial on Deep learning and Applications
Ā 
Introduction to Big Data/Machine Learning
Introduction to Big Data/Machine LearningIntroduction to Big Data/Machine Learning
Introduction to Big Data/Machine Learning
Ā 
Artificial neural network
Artificial neural networkArtificial neural network
Artificial neural network
Ā 
Hadoop and Machine Learning
Hadoop and Machine LearningHadoop and Machine Learning
Hadoop and Machine Learning
Ā 
How to Interview a Data Scientist
How to Interview a Data ScientistHow to Interview a Data Scientist
How to Interview a Data Scientist
Ā 
Data By The People, For The People
Data By The People, For The PeopleData By The People, For The People
Data By The People, For The People
Ā 
A Statistician's View on Big Data and Data Science (Version 1)
A Statistician's View on Big Data and Data Science (Version 1)A Statistician's View on Big Data and Data Science (Version 1)
A Statistician's View on Big Data and Data Science (Version 1)
Ā 
Hands-on Deep Learning in Python
Hands-on Deep Learning in PythonHands-on Deep Learning in Python
Hands-on Deep Learning in Python
Ā 
10 Lessons Learned from Building Machine Learning Systems
10 Lessons Learned from Building Machine Learning Systems10 Lessons Learned from Building Machine Learning Systems
10 Lessons Learned from Building Machine Learning Systems
Ā 
Big Data [sorry] & Data Science: What Does a Data Scientist Do?
Big Data [sorry] & Data Science: What Does a Data Scientist Do?Big Data [sorry] & Data Science: What Does a Data Scientist Do?
Big Data [sorry] & Data Science: What Does a Data Scientist Do?
Ā 
How to Become a Data Scientist
How to Become a Data ScientistHow to Become a Data Scientist
How to Become a Data Scientist
Ā 
A tutorial on deep learning at icml 2013
A tutorial on deep learning at icml 2013A tutorial on deep learning at icml 2013
A tutorial on deep learning at icml 2013
Ā 
Introduction to Mahout and Machine Learning
Introduction to Mahout and Machine LearningIntroduction to Mahout and Machine Learning
Introduction to Mahout and Machine Learning
Ā 
Deep Learning for Natural Language Processing
Deep Learning for Natural Language ProcessingDeep Learning for Natural Language Processing
Deep Learning for Natural Language Processing
Ā 
Machine Learning and Data Mining: 12 Classification Rules
Machine Learning and Data Mining: 12 Classification RulesMachine Learning and Data Mining: 12 Classification Rules
Machine Learning and Data Mining: 12 Classification Rules
Ā 
Myths and Mathemagical Superpowers of Data Scientists
Myths and Mathemagical Superpowers of Data ScientistsMyths and Mathemagical Superpowers of Data Scientists
Myths and Mathemagical Superpowers of Data Scientists
Ā 
Tips for data science competitions
Tips for data science competitionsTips for data science competitions
Tips for data science competitions
Ā 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networks
Ā 
10 R Packages to Win Kaggle Competitions
10 R Packages to Win Kaggle Competitions10 R Packages to Win Kaggle Competitions
10 R Packages to Win Kaggle Competitions
Ā 
Artificial Intelligence Presentation
Artificial Intelligence PresentationArtificial Intelligence Presentation
Artificial Intelligence Presentation
Ā 

Ƅhnlich wie An Introduction to Supervised Machine Learning and Pattern Classification: The Big Picture

Introduction to conventional machine learning techniques
Introduction to conventional machine learning techniquesIntroduction to conventional machine learning techniques
Introduction to conventional machine learning techniquesXavier Rafael Palou
Ā 
Machine Learning ebook.pdf
Machine Learning ebook.pdfMachine Learning ebook.pdf
Machine Learning ebook.pdfHODIT12
Ā 
1_5_AI_edx_ml_51intro_240204_104838machine learning lecture 1
1_5_AI_edx_ml_51intro_240204_104838machine learning lecture 11_5_AI_edx_ml_51intro_240204_104838machine learning lecture 1
1_5_AI_edx_ml_51intro_240204_104838machine learning lecture 1MostafaHazemMostafaa
Ā 
Lecture 02: Machine Learning for Language Technology - Decision Trees and Nea...
Lecture 02: Machine Learning for Language Technology - Decision Trees and Nea...Lecture 02: Machine Learning for Language Technology - Decision Trees and Nea...
Lecture 02: Machine Learning for Language Technology - Decision Trees and Nea...Marina Santini
Ā 
Data mining classifiers.
Data mining classifiers.Data mining classifiers.
Data mining classifiers.ShwetaPatil174
Ā 
Lecture 8: Decision Trees & k-Nearest Neighbors
Lecture 8: Decision Trees & k-Nearest NeighborsLecture 8: Decision Trees & k-Nearest Neighbors
Lecture 8: Decision Trees & k-Nearest NeighborsMarina Santini
Ā 
. An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic .... An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic ...butest
Ā 
Presentation on Text Classification
Presentation on Text ClassificationPresentation on Text Classification
Presentation on Text ClassificationSai Srinivas Kotni
Ā 
know Machine Learning Basic Concepts.pdf
know Machine Learning Basic Concepts.pdfknow Machine Learning Basic Concepts.pdf
know Machine Learning Basic Concepts.pdfhemangppatel
Ā 
Machine Learning and Real-World Applications
Machine Learning and Real-World ApplicationsMachine Learning and Real-World Applications
Machine Learning and Real-World ApplicationsMachinePulse
Ā 
Large Scale Data Clustering: an overview
Large Scale Data Clustering: an overviewLarge Scale Data Clustering: an overview
Large Scale Data Clustering: an overviewVahid Mirjalili
Ā 
Machine learning for_finance
Machine learning for_financeMachine learning for_finance
Machine learning for_financeStefan Duprey
Ā 
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...Association for Computational Linguistics
Ā 
Machine Learning: Foundations Course Number 0368403401
Machine Learning: Foundations Course Number 0368403401Machine Learning: Foundations Course Number 0368403401
Machine Learning: Foundations Course Number 0368403401butest
Ā 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273Abutest
Ā 
MS CS - Selecting Machine Learning Algorithm
MS CS - Selecting Machine Learning AlgorithmMS CS - Selecting Machine Learning Algorithm
MS CS - Selecting Machine Learning AlgorithmKaniska Mandal
Ā 
My7class
My7classMy7class
My7classketan533
Ā 
Free Ebooks Download ! Edhole.com
Free Ebooks Download ! Edhole.comFree Ebooks Download ! Edhole.com
Free Ebooks Download ! Edhole.comEdhole.com
Ā 
Machine Learning and Statistical Analysis
Machine Learning and Statistical AnalysisMachine Learning and Statistical Analysis
Machine Learning and Statistical Analysisbutest
Ā 

Ƅhnlich wie An Introduction to Supervised Machine Learning and Pattern Classification: The Big Picture (20)

Introduction to conventional machine learning techniques
Introduction to conventional machine learning techniquesIntroduction to conventional machine learning techniques
Introduction to conventional machine learning techniques
Ā 
Machine Learning ebook.pdf
Machine Learning ebook.pdfMachine Learning ebook.pdf
Machine Learning ebook.pdf
Ā 
1_5_AI_edx_ml_51intro_240204_104838machine learning lecture 1
1_5_AI_edx_ml_51intro_240204_104838machine learning lecture 11_5_AI_edx_ml_51intro_240204_104838machine learning lecture 1
1_5_AI_edx_ml_51intro_240204_104838machine learning lecture 1
Ā 
Lecture 02: Machine Learning for Language Technology - Decision Trees and Nea...
Lecture 02: Machine Learning for Language Technology - Decision Trees and Nea...Lecture 02: Machine Learning for Language Technology - Decision Trees and Nea...
Lecture 02: Machine Learning for Language Technology - Decision Trees and Nea...
Ā 
Data mining classifiers.
Data mining classifiers.Data mining classifiers.
Data mining classifiers.
Ā 
Clustering
ClusteringClustering
Clustering
Ā 
Lecture 8: Decision Trees & k-Nearest Neighbors
Lecture 8: Decision Trees & k-Nearest NeighborsLecture 8: Decision Trees & k-Nearest Neighbors
Lecture 8: Decision Trees & k-Nearest Neighbors
Ā 
. An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic .... An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic ...
Ā 
Presentation on Text Classification
Presentation on Text ClassificationPresentation on Text Classification
Presentation on Text Classification
Ā 
know Machine Learning Basic Concepts.pdf
know Machine Learning Basic Concepts.pdfknow Machine Learning Basic Concepts.pdf
know Machine Learning Basic Concepts.pdf
Ā 
Machine Learning and Real-World Applications
Machine Learning and Real-World ApplicationsMachine Learning and Real-World Applications
Machine Learning and Real-World Applications
Ā 
Large Scale Data Clustering: an overview
Large Scale Data Clustering: an overviewLarge Scale Data Clustering: an overview
Large Scale Data Clustering: an overview
Ā 
Machine learning for_finance
Machine learning for_financeMachine learning for_finance
Machine learning for_finance
Ā 
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...
Chris Dyer - 2017 - Neural MT Workshop Invited Talk: The Neural Noisy Channel...
Ā 
Machine Learning: Foundations Course Number 0368403401
Machine Learning: Foundations Course Number 0368403401Machine Learning: Foundations Course Number 0368403401
Machine Learning: Foundations Course Number 0368403401
Ā 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273A
Ā 
MS CS - Selecting Machine Learning Algorithm
MS CS - Selecting Machine Learning AlgorithmMS CS - Selecting Machine Learning Algorithm
MS CS - Selecting Machine Learning Algorithm
Ā 
My7class
My7classMy7class
My7class
Ā 
Free Ebooks Download ! Edhole.com
Free Ebooks Download ! Edhole.comFree Ebooks Download ! Edhole.com
Free Ebooks Download ! Edhole.com
Ā 
Machine Learning and Statistical Analysis
Machine Learning and Statistical AnalysisMachine Learning and Statistical Analysis
Machine Learning and Statistical Analysis
Ā 

KĆ¼rzlich hochgeladen

ALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptxALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptxolyaivanovalion
Ā 
Escorts Service Kumaraswamy Layout ā˜Ž 7737669865ā˜Ž Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ā˜Ž 7737669865ā˜Ž Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ā˜Ž 7737669865ā˜Ž Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ā˜Ž 7737669865ā˜Ž Book Your One night Stand (B...amitlee9823
Ā 
Junnasandra Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore...Junnasandra Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore...amitlee9823
Ā 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz1
Ā 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxolyaivanovalion
Ā 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxolyaivanovalion
Ā 
Sampling (random) method and Non random.ppt
Sampling (random) method and Non random.pptSampling (random) method and Non random.ppt
Sampling (random) method and Non random.pptDr. Soumendra Kumar Patra
Ā 
Call Girls Hsr Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...amitlee9823
Ā 
Call Girls Bannerghatta Road Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Ser...amitlee9823
Ā 
Call Girls Begur Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Bangalore
Call Girls Begur Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service BangaloreCall Girls Begur Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Bangalore
Call Girls Begur Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Bangaloreamitlee9823
Ā 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxolyaivanovalion
Ā 
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdfAccredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdfadriantubila
Ā 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxolyaivanovalion
Ā 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...SUHANI PANDEY
Ā 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxolyaivanovalion
Ā 
BDSMāš”Call Girls in Mandawali Delhi >ą¼’8448380779 Escort Service
BDSMāš”Call Girls in Mandawali Delhi >ą¼’8448380779 Escort ServiceBDSMāš”Call Girls in Mandawali Delhi >ą¼’8448380779 Escort Service
BDSMāš”Call Girls in Mandawali Delhi >ą¼’8448380779 Escort ServiceDelhi Call girls
Ā 
Ravak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxRavak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxolyaivanovalion
Ā 
Call Girls in Sarai Kale Khan Delhi šŸ’Æ Call Us šŸ”9205541914 šŸ”( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi šŸ’Æ Call Us šŸ”9205541914 šŸ”( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi šŸ’Æ Call Us šŸ”9205541914 šŸ”( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi šŸ’Æ Call Us šŸ”9205541914 šŸ”( Delhi) Escorts S...Delhi Call girls
Ā 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxolyaivanovalion
Ā 

KĆ¼rzlich hochgeladen (20)

ALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptxALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptx
Ā 
Escorts Service Kumaraswamy Layout ā˜Ž 7737669865ā˜Ž Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ā˜Ž 7737669865ā˜Ž Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ā˜Ž 7737669865ā˜Ž Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ā˜Ž 7737669865ā˜Ž Book Your One night Stand (B...
Ā 
Junnasandra Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore...Junnasandra Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: šŸ“ 7737669865 šŸ“ High Profile Model Escorts | Bangalore...
Ā 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
Ā 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFx
Ā 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFx
Ā 
Sampling (random) method and Non random.ppt
Sampling (random) method and Non random.pptSampling (random) method and Non random.ppt
Sampling (random) method and Non random.ppt
Ā 
Call Girls Hsr Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Ba...
Ā 
Call Girls Bannerghatta Road Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Ser...
Ā 
Call Girls Begur Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Bangalore
Call Girls Begur Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service BangaloreCall Girls Begur Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Bangalore
Call Girls Begur Just Call šŸ‘— 7737669865 šŸ‘— Top Class Call Girl Service Bangalore
Ā 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptx
Ā 
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdfAccredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
Ā 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptx
Ā 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
Ā 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptx
Ā 
BDSMāš”Call Girls in Mandawali Delhi >ą¼’8448380779 Escort Service
BDSMāš”Call Girls in Mandawali Delhi >ą¼’8448380779 Escort ServiceBDSMāš”Call Girls in Mandawali Delhi >ą¼’8448380779 Escort Service
BDSMāš”Call Girls in Mandawali Delhi >ą¼’8448380779 Escort Service
Ā 
CHEAP Call Girls in Saket (-DELHI )šŸ” 9953056974šŸ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )šŸ” 9953056974šŸ”(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )šŸ” 9953056974šŸ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )šŸ” 9953056974šŸ”(=)/CALL GIRLS SERVICE
Ā 
Ravak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxRavak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptx
Ā 
Call Girls in Sarai Kale Khan Delhi šŸ’Æ Call Us šŸ”9205541914 šŸ”( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi šŸ’Æ Call Us šŸ”9205541914 šŸ”( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi šŸ’Æ Call Us šŸ”9205541914 šŸ”( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi šŸ’Æ Call Us šŸ”9205541914 šŸ”( Delhi) Escorts S...
Ā 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptx
Ā 

An Introduction to Supervised Machine Learning and Pattern Classification: The Big Picture

  • 1. Practical Data Science An Introduction to Supervised Machine Learning and Pattern Classiļ¬cation: The Big Picture Michigan State University NextGen Bioinformatics Seminars - 2015 Sebastian Raschka Feb. 11, 2015
  • 2. A Little Bit About Myself ... Developing software & methods for - Protein ligand docking - Large scale drug/inhibitor discovery PhD candidate in Dr. L. Kuhnā€™s Lab: and some other machine learning side-projects ā€¦
  • 3. What is Machine Learning? http://drewconway.com/zia/2013/3/26/the-data-science-venn-diagram "Field of study that gives computers the ability to learn without being explicitly programmed.ā€ (Arthur Samuel, 1959) By Phillip Taylor [CC BY 2.0]
  • 5. Examples of Machine Learning http://googleresearch.blogspot.com/2014/11/a-picture-is-worth-thousand-coherent.html By Steve Jurvetson [CC BY 2.0] Self-driving cars Photo search and many, many more ... Recommendation systems http://commons.wikimedia.org/wiki/File:Netļ¬‚ix_logo.svg [public domain]
  • 6. How many of you have used machine learning before?
  • 7. Our Agenda ā€¢ Concepts and the big picture ā€¢ Workļ¬‚ow ā€¢ Practical tips & good habits
  • 8. Learning ā€¢ Labeled data ā€¢ Direct feedback ā€¢ Predict outcome/future ā€¢ Decision process ā€¢ Reward system ā€¢ Learn series of actions ā€¢ No labels ā€¢ No feedback ā€¢ ā€œFind hidden structureā€ Unsupervised Supervised Reinforcement
  • 9. Unsupervised learning Supervised learning Clustering: [DBSCAN on a toy dataset] Classiļ¬cation: [SVM on 2 classes of the Wine dataset] Regression: [Soccer Fantasy Score prediction] Todayā€™s topic Supervised LearningUnsupervised Learning
  • 10. Instances (samples, observations) Features (attributes, dimensions) Classes (targets) Nomenclature sepal_length sepal_width petal_length petal_width class 1 5.1 3.5 1.4 0.2 setosa 2 4.9 3.0 1.4 0.2 setosa ā€¦ ā€¦ ā€¦ ā€¦ ā€¦ ā€¦ 50 6.4 3.2 4.5 1.5 veriscolor ā€¦ ā€¦ ā€¦ ā€¦ ā€¦ ā€¦ 150 5.9 3.0 5.1 1.8 virginica https://archive.ics.uci.edu/ml/datasets/Iris IRIS
  • 11. Classiļ¬cation x1 x2 class1 class2 1) Learn from training data 2) Map unseen (new) data ?
  • 12. Feature Extraction Feature Selection Dimensionality Reduction Feature Scaling Raw Data Collection Pre-Processing Sampling Test Dataset Training Dataset Learning Algorithm Training Post-Processing Cross Validation Final Classiļ¬cation/ Regression Model New DataPre-Processing Reļ¬nement Prediction Split Supervised Learning Sebastian Raschka 2014 Missing Data Performance Metrics Model Selection Hyperparameter Optimization This work is licensed under a Creative Commons Attribution 4.0 International License. Final Model Evaluation
  • 13. Feature Extraction Feature Selection Dimensionality Reduction Feature Scaling Raw Data Collection Pre-Processing Sampling Test Dataset Training Dataset Learning Algorithm Training Post-Processing Cross Validation Final Classiļ¬cation/ Regression Model New DataPre-Processing Reļ¬nement Prediction Split Supervised Learning Sebastian Raschka 2014 Missing Data Performance Metrics Model Selection Hyperparameter Optimization This work is licensed under a Creative Commons Attribution 4.0 International License. Final Model Evaluation
  • 14. A Few Common Classiļ¬ers Decision Tree Perceptron Naive Bayes Ensemble Methods: Random Forest, Bagging, AdaBoost Support Vector Machine K-Nearest Neighbor Logistic Regression Artiļ¬cial Neural Network / Deep Learning
  • 15. Discriminative Algorithms Generative Algorithms ā€¢ Models a more general problem: how the data was generated. ā€¢ I.e., the distribution of the class; joint probability distribution p(x,y). ā€¢ Naive Bayes, Bayesian Belief Network classiļ¬er, Restricted Boltzmann Machine ā€¦ ā€¢ Map x ā†’ y directly. ā€¢ E.g., distinguish between people speaking different languages without learning the languages. ā€¢ Logistic Regression, SVM, Neural Networks ā€¦
  • 16. Examples of Discriminative Classiļ¬ers: Perceptron xi1 xi2 w1 w2 Ī£ yi y = wTx = w0 + w1x1 + w2x2 1 F. Rosenblatt. The perceptron, a perceiving and recognizing automaton Project Para. Cornell Aeronautical Laboratory, 1957. x1 x2 y āˆˆ {-1,1} w0 wj = weight xi = training sample yi = desired output yi = actual output t = iteration step Ī· = learning rate Īø = threshold (here 0) update rule: wj(t+1) = wj(t) + Ī·(yi - yi)xi 1 if wTxi ā‰„ Īø -1 otherwise ^ ^ ^ ^ yi ^ until t+1 = max iter or error = 0
  • 17. Discriminative Classiļ¬ers: Perceptron F. Rosenblatt. The perceptron, a perceiving and recognizing automaton Project Para. Cornell Aeronautical Laboratory, 1957. - Binary classiļ¬er (one vs all, OVA) - Convergence problems (set n iterations) - Modiļ¬cation: stochastic gradient descent - ā€œModernā€ perceptron: Support Vector Machine (maximize margin) - Multilayer perceptron (MLP) xi1 xi2 w1 w2 Ī£ yi 1 y āˆˆ {-1,1} w0 ^ x1 x2
  • 18. Generative Classiļ¬ers: Naive Bayes Bayes Theorem: P(Ļ‰j | xi) = P(xi | Ļ‰j) P(Ļ‰j) P(xi) Posterior probability = Likelihood x Prior probability Evidence Iris example: P(ā€œSetosa"| xi), xi = [4.5 cm, 7.4 cm]
  • 19. Generative Classiļ¬ers: Naive Bayes Decision Rule: Bayes Theorem: P(Ļ‰j | xi) = P(xi | Ļ‰j) P(Ļ‰j) P(xi) pred. class label Ļ‰j argmax P(Ļ‰j | xi) i = 1, ā€¦, m e.g., j āˆˆ {Setosa, Versicolor, Virginica}
  • 20. Class-conditional probability (here Gaussian kernel): Generative Classiļ¬ers: Naive Bayes Prior probability: Evidence: (cancels out) (class frequency) P(Ļ‰j | xi) = P(xi | Ļ‰j) P(Ļ‰j) P(xi) P(Ļ‰j) = NĻ‰j Nc P(xik |Ļ‰j) = 1 āˆš (2 Ļ€ ĻƒĻ‰j 2) exp ( )- (xik - Ī¼Ļ‰j)2 2ĻƒĻ‰j 2 P(xi |Ļ‰j) P(xik |Ļ‰j)
  • 21. Generative Classiļ¬ers: Naive Bayes - Naive conditional independence assumption typically violated - Works well for small datasets - Multinomial model still quite popular for text classiļ¬cation (e.g., spam ļ¬lter)
  • 22. Non-Parametric Classiļ¬ers: K-Nearest Neighbor - Simple! - Lazy learner - Very susceptible to curse of dimensionality k=3 e.g., k=1
  • 23. Iris Example Setosa Virginica Versicolor k = 3 mahalanobis dist. uniform weights C = 3 depth = 2
  • 24. Decision Tree Entropy = depth = 4 petal length <= 2.45? petal length <= 4.75? Setosa Virginica Versicolor Yes No e.g., 2 (- 0.5 log2(0.5)) = 1 āˆ‘āˆ’pi logk pi i Information Gain = entropy(parent) ā€“ [avg entropy(children)] NoYes depth = 2
  • 25. "No Free Lunch" :( Roughly speaking: ā€œNo one model works best for all possible situations.ā€ Our model is a simpliļ¬cation of reality Simpliļ¬cation is based on assumptions (model bias) Assumptions fail in certain situations D. H. Wolpert. The supervised learning no-free-lunch theorems. In Soft Computing and Industry, pages 25ā€“42. Springer, 2002.
  • 26. Which Algorithm? ā€¢ What is the size and dimensionality of my training set? ā€¢ Is the data linearly separable? ā€¢ How much do I care about computational efļ¬ciency? - Model building vs. real-time prediction time - Eager vs. lazy learning / on-line vs. batch learning - prediction performance vs. speed ā€¢ Do I care about interpretability or should it "just work well?" ā€¢ ...
  • 27. Feature Extraction Feature Selection Dimensionality Reduction Feature Scaling Raw Data Collection Pre-Processing Sampling Test Dataset Training Dataset Learning Algorithm Training Post-Processing Cross Validation Final Classiļ¬cation/ Regression Model New DataPre-Processing Reļ¬nement Prediction Split Supervised Learning Sebastian Raschka 2014 Missing Data Performance Metrics Model Selection Hyperparameter Optimization This work is licensed under a Creative Commons Attribution 4.0 International License. Final Model Evaluation
  • 28. Missing Values: - Remove features (columns) - Remove samples (rows) - Imputation (mean, nearest neighbor, ā€¦) Sampling: - Random split into training and validation sets - Typically 60/40, 70/30, 80/20 - Donā€™t use validation set until the very end! (overļ¬tting) Feature Scaling: e.g., standardization: - Faster convergence (gradient descent) - Distances on same scale (k-NN with Euclidean distance) - Mean centering for free - Normal distributed data - Numerical stability by avoiding small weights z = xik - Ī¼k Ļƒk (use same parameters for the test/new data!)
  • 29. Categorical Variables color size prize class label 0 green M 10.1 class1 1 red L 13.5 class2 2 blue XL 15.3 class1 ordinalnominal green ā†’ (1,0,0) red ā†’ (0,1,0) blue ā†’ (0,0,1) class label color=blue color=green color=red prize size 0 0 0 1 0 10.1 1 1 1 0 0 1 13.5 2 2 0 1 0 0 15.3 3 M ā†’ 1 L ā†’ 2 XL ā†’ 3
  • 30. Feature Extraction Feature Selection Dimensionality Reduction Feature Scaling Raw Data Collection Pre-Processing Sampling Test Dataset Training Dataset Learning Algorithm Training Post-Processing Cross Validation Final Classiļ¬cation/ Regression Model New DataPre-Processing Reļ¬nement Prediction Split Supervised Learning Sebastian Raschka 2014 Missing Data Performance Metrics Model Selection Hyperparameter Optimization This work is licensed under a Creative Commons Attribution 4.0 International License. Final Model Evaluation
  • 31. Generalization Error and Overļ¬tting How well does the model perform on unseen data?
  • 32. Generalization Error and Overļ¬tting
  • 33. Error Metrics: Confusion Matrix TP [Linear SVM on sepal/petal lengths] TN FN FP here: ā€œsetosaā€ = ā€œpositiveā€
  • 34. Error Metrics TP [Linear SVM on sepal/petal lengths] TN FN FP here: ā€œsetosaā€ = ā€œpositiveā€ TP + TN FP +FN +TP +TN Accuracy = = 1 - Error FP N TP P False Positive Rate = TP TP + FP Precision = True Positive Rate = (Recall) ā€œmicroā€ and ā€œmacroā€ averaging for multi-class
  • 36. Test set Training dataset Test dataset Complete dataset Test set Test set Test set 1st iteration calc. error calc. error calc. error calc. error calculate avg. error k-fold cross-validation (k=4): 2nd iteration 3rd iteration 4th iteration fold 1 fold 2 fold 3 fold 4 Model Selection
  • 38. Feature Selection - Domain knowledge - Variance threshold - Exhaustive search - Decision trees - ā€¦ IMPORTANT! (Noise, overļ¬tting, curse of dimensionality, efļ¬ciency) X = [x1, x2, x3, x4]start: stop: (if d = k) X = [x1, x3, x4] X = [x1, x3] Simplest example: Greedy Backward Selection
  • 39. Dimensionality Reduction ā€¢ Transformation onto a new feature subspace ā€¢ e.g., Principal Component Analysis (PCA) ā€¢ Find directions of maximum variance ā€¢ Retain most of the information
  • 40. 0. Standardize data 1. Compute covariance matrix z = xik - Ī¼k Ļƒik = āˆ‘ (xij - Āµj) (xik - Āµk) Ļƒk 1 in -1 Ļƒ2 1 Ļƒ12 Ļƒ13 Ļƒ14 Ļƒ21 Ļƒ2 2 Ļƒ23 Ļƒ24 Ļƒ31 Ļƒ32 Ļƒ2 3 Ļƒ34 Ļƒ41 Ļƒ42 Ļƒ43 Ļƒ2 4 āˆ‘ = PCA in 3 Steps
  • 41. 2. Eigendecomposition and sorting eigenvalues PCA in 3 Steps X v = Ī» v Eigenvectors [[ 0.52237162 -0.37231836 -0.72101681 0.26199559] [-0.26335492 -0.92555649 0.24203288 -0.12413481] [ 0.58125401 -0.02109478 0.14089226 -0.80115427] [ 0.56561105 -0.06541577 0.6338014 0.52354627]] Eigenvalues [ 2.93035378 0.92740362 0.14834223 0.02074601] (from high to low)
  • 42. 3. Select top k eigenvectors and transform data PCA in 3 Steps Eigenvectors [[ 0.52237162 -0.37231836 -0.72101681 0.26199559] [-0.26335492 -0.92555649 0.24203288 -0.12413481] [ 0.58125401 -0.02109478 0.14089226 -0.80115427] [ 0.56561105 -0.06541577 0.6338014 0.52354627]] Eigenvalues [ 2.93035378 0.92740362 0.14834223 0.02074601] [First 2 PCs of Iris]
  • 44. Non-Linear Problems - XOR gate k=11 uniform weights C=1 C=1000, gamma=0.1 depth=4
  • 45. Kernel Trick Kernel function Kernel Map onto high-dimensional space (non-linear combinations)
  • 46. Kernel Trick Trick: No explicit dot product! Radius Basis Function (RBF) Kernel:
  • 47. Kernel PCA PC1, linear PCA PC1, kernel PCA
  • 48. Feature Extraction Feature Selection Dimensionality Reduction Feature Scaling Raw Data Collection Pre-Processing Sampling Test Dataset Training Dataset Learning Algorithm Training Post-Processing Cross Validation Final Classiļ¬cation/ Regression Model New DataPre-Processing Reļ¬nement Prediction Split Supervised Learning Sebastian Raschka 2014 Missing Data Performance Metrics Model Selection Hyperparameter Optimization This work is licensed under a Creative Commons Attribution 4.0 International License. Final Model Evaluation
  • 51. Inspiring Literature P. N. Klein. Coding the Matrix: Linear Algebra Through Computer Science Applications. Newtonian Press, 2013. R. Schutt and C. Oā€™Neil. Doing Data Science: Straight Talk from the Frontline. Oā€™Reilly Media, Inc., 2013. S. Gutierrez. Data Scientists at Work. Apress, 2014. R. O. Duda, P. E. Hart, and D. G. Stork. Pattern classiļ¬cation. 2nd. Edition. New York, 2001.
  • 55. class1 class2 The problem of overļ¬tting Generalization error!