AI Platform

https://www.dominodatalab.com/

Recommended by a colleague.

—-

Open Source
https://mlflow.org/

—-

Connectors:
https://www.cdata.com/

AI – Model Binary Files

We can store trained models in a binary file for later use.
1. pickle
2. cpickle
3. joblib

—–
joblib works especially well with NumPy arrays which are used by sklearn so depending on the classifier type you use you might have performance and size benefits using joblib.

Otherwise pickle does work correctly so saving a trained classifier and loading it again will produce the same results no matter which of the serialization libraries you use. See also the docs of sklearn on this topic.

Please note that joblib is included in sklearn.

Copied from: https://stackoverflow.com/questions/36794981/difference-between-saving-a-classifier-with-pickle-and-joblib-dump

—–
https://stackoverflow.com/questions/12615525/what-are-the-different-use-cases-of-joblib-versus-pickle
—–

Test the following for your model
1. Final binary file size
2. Total foot memory footprint
3. Time to load

—-

What is AI System?

AI is having the following categories:
Expert systems
Machine learning
Natural language processing
Computer vision
Automated speech recognition
AI Planning

Reference: https://codebots.com/ai-powered-bots/6-technologies-behind-ai

-o-

Expert Systems: https://www.tutorialspoint.com/artificial_intelligence/artificial_intelligence_expert_systems.htm

AI Planning:
https://researcher.watson.ibm.com/researcher/view_group.php?id=8432

Constraint Programming

https://en.wikipedia.org/wiki/Constraint_programming

Solvers

https://www.solver.com/solver-tutorial-defining-constraints

https://labix.org/python-constraint
Examples on: 8 Queen problem, Magic Squares,…etc

Java Library
http://www.choco-solver.org/

Machine learning algorithm cheat sheet

https://docs.microsoft.com/en-us/azure/machine-learning/studio/algorithm-cheat-sheet

microsoft-machine-learning-algorithm-cheat-sheet-v6