Last active
July 16, 2022 10:21
-
-
Save sunsided/1737fb6922d126374009fb14e5027d47 to your computer and use it in GitHub Desktop.
Effects of emergence on example machine learning problems (Shahab, 2017)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Example ML problem | Feature space | Feature noise | Emergence barrier | Prediction success | |
---|---|---|---|---|---|
Character recognition | handwritten character images | high | none | high | |
Speech recognition | sound waves | high | none | high | |
Weather predictions | climate sensor data | high | weak | high | |
Recommendation system | historic preferences, likes, etc. | low | weak | moderate | |
Ad-click prediction | historic click behavior | low | weak | moderate | |
Device failure prediction | sensor data | high | weak | moderate | |
Healthcare outcome predicitons | patient data, vital signs, behavior, etc. | high | strong | low | |
Melting/boiling point prediction | molecular/atomic structure | low | strong | low | |
Stock prediction | historic stock value, news articles, etc. | low | strong | low |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment