Google

For managers and developers

presentation.png
 

Introduction to ML

Key concepts, use cases, possibilities, and limitations. How to choose the best ML solution / tools / APIs / platforms for your organization.

directions.png
 

Decisions from predictions

Interpreting predictive models, confidence values, and errors. Using predictions to create new value in your application / business / process.

report.png
 

Defining your use cases

Understanding and using the Machine Learning Canvas to formalize ML problems. Identifying “low-hanging fruit” in ML usage for your own project.

For developers

brain
 

Learning techniques

  • Supervised: Decision Trees, Random Forests, Gradient Boosting, Logistic Regression
  • Unsupervised: Anomaly Detection (isolation forests), Clustering (k-means)
  • Deep Learning: Neural Networks, Transfer Learning
workflow.png
 

Workflows

  • Data processing pipelines: cleaning, natural language processing, feature engineering
  • Model selection: evaluation, performance metrics, cross-validation, parameter tuning
  • Deployment in production
  • REST APIs for real-world ML
 

Tools

  • Basics: Docker, Anaconda, Jupyter, Flask
  • Open source ML: Scikit-learn, SKLL, Xgboost, Hyperopt, Keras, Tensorflow, Pandas
  • ML platforms: Dataiku, BigML, Microsoft Azure ML