This winter/spring I've been hosting a TWIML study group for the IBM AI Enterprise Workflow specialization on Coursera. The specialization consists of six courses that progressively walk the learner through the experience of building and deploying a real-world enterprise AI solutions, from establishing business priorities and a data pipeline through to deploying and managing your model in production.
This repository contains my notes and notebooks from the courses. The repo is organized by course, and within each course the filename will denote which week the resource pertains.
The notes (*-study-group-slides.pdf) were presented during our Saturday study group sessions. You can access the recordings of these via the YouTube playlist.
See below for the coverage area of each course module:
| Module | Topic |
|---|---|
| Course 1 Week 1 | Course intro |
| Course 1 Week 2 | Data ingestion, cleaning, parsing, assembly |
| Course 2 Week 1 | Exploratory data analysis & visualization |
| Course 2 Week 2 | Estimation and NHT |
| Course 3 Week 1 | Data transformation and feature engineering |
| Course 3 Week 2 | Pattern recognition and data mining best practices |
| Course 4 Week 1 | Model evaluation and performance metrics |
| Course 4 Week 2 | Building machine learning and deep learning models |
| Course 5 Week 1 | Deploying models |
| Course 5 Week 2 | Deploying models using Spark |
| Course 6 Week 1 | Feedback loops and monitoring |
| Course 6 Week 2 | Hands on with OpenScale and Kubernetes |
| Course 6 Week 3 | Captsone project week 1 |
| Course 6 Week 4 | Captsone project week 2 |
The TWIML Community is a global network of machine learning, deep learning and AI practitioners and enthusiasts.
We organize ongoing educational programs including study groups for several popular ML/AI courses such as Fast.ai Deep Learning, Machine learning and NLP, Stanford CS224N, Deeplearning.ai and more. We also host several special interest groups focused on topics like Swift for Tensorflow, and competing in Kaggle competitions.
For more information, or to join us, visit twimlai.com/community.