Azure ML Training - Deep Dive
3 likes682 views
This document provides an overview of Microsoft Azure Machine Learning Studio capabilities. It includes infographics and descriptions of Azure ML Studio, a platform for building and deploying machine learning experiments graphically using over 100 modules. Examples are given of data cleansing and tuning model hyperparameters. References are made to resources on machine learning algorithms, performance measures, and the book Machine Learning Yearning by Andrew Ng.
Azure ML Training - Deep Dive
- 9. IF Other-Delinquent-Accounts > 2 and Number-Delinquent-Billing-Cycles >1 THEN DENAY CREDIT IF Other-Delinquent-Accounts = 0 and Income > $30k THEN GRANT CREDIT
- 12. 5 questions that data science answers
- 22. Equation – E(y) = b0 + b1x
- 30. Demo of SVM – Jupyter Notebook
- 33. Platform for emerging data scientists to graphically build and deploy experiments • Rapid experiment composition • > 100 easily configured modules for data prep, training, evaluation • Extensibility through R & Python • Serverless training and deployment Some numbers: • 100’s of thousands of deployed models serving billions of requests
- 43. Microsoft Azure ML Studio Capabilities Overview
- 44. Azure Machine Learning Studio
- 60. Data Cleansing Example 1 Data Cleansing Example 2
- 63. 1 2 1 0 1 2 5 0
- 82. Tune model hyper Parameters
- 89. Machine Learning Yearning by Andrew Ng
- 90. Machine Learning Yearning by Andrew Ng
- 92. Machine Learning for Muggles Too Tour of Machine Learning Algorithms Performance Measures in Azure ML Azure ML Infographic Azure ML Capabilities Azure AI Gallery ML Performance Cheatsheet Machine Learning Yearning by Andrew NG EXSILIO Data Science Youtube Channel
- 97. Step 1 - Define the Business Problem Step 2 – Utilize your Data and Extract Features Step 3 – Develop your ML model through iterations Step 4 – Deploy the Model and make measurements Step 5 – Monitor and Fine Models Performance