Machine Learning with MATLAB Leuven Statistics Day2014 Rachid Adarghal, Account Manager Jean-Philippe Villaréal, Application Engineer 2014 The MathWorks, Inc. 1
Side note: Design of Experiments with MATLAB 2
What You Will Learn Get an overview of Machine Learning Machine learning models and techniques available in MATLAB MATLAB as an interactive environment Evaluate and choose the best algorithm 3
Machine Learning Characteristics Lots of data (many variables) System too complex to understand the governing equation 4
Domains of Application Handwriting recognition Autonomous vehicles DNA sequencing / Genomics Cancer tumor classification Social Network Analysis Astronomical Data Analysis Market Segmentation Organizing Computer Cluster for efficiency Spam / non spam email classification Hearing headsets: optimizing signal (Cocktail party) Shazam / SoundHound FingerPrinting 5
Challenges Machine Learning Lots of data, with many variables (predictors) Data is too complex to know the governing equation Significant technical expertise required Black box modelling No one size fits all approach: Requires an iterative approach: Try multiple algorithms, see what works best Time consuming to conduct the analysis Know-how required to debug your algorithm efficiently 6
MATLAB Solutions Strong environment for interactive exploration Algorithms and Apps to get started Clustering, Classification, Regression Neural Network app, Curve fitting app Easy to evaluate, iterate, and choose the best algorithm Parallel Computing Deployment for Data Analytics workflows 7
Overview Machine Learning Type of Learning Categories of Algorithms Unsupervised Learning Clustering Machine Learning Group and interpret data based only on input data Recommender systems Supervised Learning Classification Develop predictive model based on both input and output data Regression 9
Unsupervised Learning k-means Clustering Partitional Clustering Overlapping Clustering Self-Organizing Maps Hierarchical clustering Fuzzy C-Means Gaussian Mixture Hidden Markov Model 10
Supervised Learning Regression Neural Networks Decision Trees Ensemble Methods Non-linear Reg. (GLM, Logistic) Linear Regression Classification Support Vector Machines Discriminant Analysis Naive Bayes Nearest Neighbor 11
Supervised Learning - Workflow Speed up Computations Select Model Data Train the Model Use for Prediction Import Data Explore Data Prepare Data Known data Known responses Model Model New Data Predicted Responses Measure Accuracy 12
Example Bank Marketing Campaign Goal: Predict if customer would subscribe to bank term deposit based on different attributes 100 90 80 Bank Marketing Campaign Misclassification Rate 70 Approach: Train a classifier using different models Percentage 60 50 40 30 20 10 No Misclassified Yes Misclassified Measure accuracy and compare models Reduce model complexity 0 Neural Net Logistic Regression Discriminant Analysis k-nearest Neighbors Naive Bayes Support VM Decision Trees TreeBagger Reduced TB Use classifier for prediction Data set downloaded from UCI Machine Learning repository http://archive.ics.uci.edu/ml/datasets/bank+marketing 13
Summary Bank Marketing Campaign Numerous predictive models with rich documentation Clustering, regression, classification Percentage 100 90 80 70 60 50 40 Bank Marketing Campaign Misclassification Rate No Misclassified Yes Misclassified 30 20 Interactive tools to help discovery Histograms, bar charts, ROC curves 10 0 Neural Net Logistic Regression Discriminant Analysis k-nearest Neighbors Naive Bayes Support VM Decision Trees TreeBagger Reduced TB Graphical Apps Built-in parallel computing support Quick prototyping Focus on modeling not programming 14
Learn More: Machine Learning with MATLAB Visit our discovery page: www.mathworks.com/machine-learning 15
Deploying / Sharing Your Application APPS Builder NE Web MATLAB Compiler.dll.lib.exe.CTF Builder JA Builder Ex Web MATLAB Coder Web MEX.exe.lib.dll 16
MathWorks Services Trainings: More that 30 course offerings Consulting Services Enhance your team Technical Support Ask questions An active community: MATLAB Central File exchange Blogs Newsletters 17
Thank you for attending! 2014 The MathWorks, Inc. 18