Machine Learning Workshop #MLDXB Al Danah, Abu Dhabi

Course details

The workshop is agnostic and features the best open source Python libraries (Pandas, scikit-learn, SKLL), APIs and ML-as-a-Service platforms (Microsoft Azure ML & Cortana Intelligence Suite, Amazon ML, BigML) for developers getting started in Machine Learning. It focuses on only two learning techniques, which turn out to be the most commonly used in practice: decision trees and ensembles.

Workshop is 2 day long and comprises 8 modules of 3 blocks of 30' each—including time for questions. Blocks are either Theory or Exercise, with at least one Exercise per module. The goal is to make you operational with machine learning at the end of the workshop.

What You Will Learn

• How Machine Learning works, its possibilities, its limitations, and the importance of data
• How to create, evaluate and deploy predictive models, via open source libraries, APIs and ML-as-a-Service platforms
• How to formulate ML problems that create value from data and that power predictive applications with innovative features

DAY 1: CORE ML

Module 1: Introduction to ML

• A data-driven digital world
• Define machine learning, why it matters, and discuss its relationship to analytics, data science, and big data.
• Key ML concepts and terminology
• Possibilities and use cases

• [Theory] Intuitions behind learning techniques and high-level overview (nearest neighbors, linear models, logistic regression, decision trees) 
  
• [Exercise] Introduction to Jupyter notebooks and Python programming 
  
• [Exercise] Creating a predictive model with scikit-learn 

• [Theory] Functioning of REST APIs and importance for ML deployment in production 
  
• [Exercise] Deploying your own models as scalable APIs with Microsoft Azure ML & Cortana Intelligence Suite, and querying them anywhere 
  
• [Theory] Overview of ML-as-a-Service and Predictive API technologies (open source, proprietary and hybrid) 

Module 4: Evaluation

• [Theory] Evaluating ML models: criteria, methods, basic performance measures and baselines 
  
• [Theory] Performance measures for classification (recall and precision) 
  
• [Exercise] MLaaS evaluation: Amazon ML and BigML (APIs, Python wrappers, command-line tools and web dashboards) 

Module 5: Model selection

• [Theory] Boosting predictions' accuracy with ensembles 
  
• [Exercise] Comparing models efficiently with SKLL 
  
• [Theory] Cross-validation 
  

Module 6: Data preparation

• [Theory] Limitations of ML 
  
• [Exercise] Feature engineering on select use cases (priority inbox, real-estate price prediction, credit scoring, churn detection) 
  
• [Exercise] Finding issues in data and fixing them in Pandas 
  

Module 7: Advanced topics: Unsupervised Learning, Deep Learning and Recommender Systems

• [Exercise] Running automated clustering and anomaly detection with Big ML's API and interpreting results 
  
• [Theory] Automatic feature extraction from text and images (illustrated with Indico's Deep Learning API) 
  
• [Theory] Building recommender systems by reduction to classification and collaborative filtering 
  

Module 8: Developing your own use case

• [Theory] Formulating your own problem: asking the right questions and specifying key aspects of the problem with the Machine Learning Canvas 
  
• [Exercise] Applying the Canvas to your own problem, or to credit scoring 
  
• Conclusions: recap of key take-away 

This workshop is ideal for:

• All of you interested in practically learning how to use Machine Learning to make your Apps and Systems more intelligent and smart. 
  
• Developers / Programmers / Software Engineers
  
• Technology Architects, Development Team Leads, Data Analysts and IT Project Manager
  
• CTOs , CIOs and CSOs
  

From industries including:

• Government/ Public Sector
  
• Technology Companies and Start-ups
  
• Banking and Finance
  
• Retail and Media
  
• Aviation
  
• Telecommunication
  
• Manufacturing
  
• Healthcare
  
• Universities and Colleges