artificial intelligence for students
14.9K views | +2 today
 
Scooped by Scott Turner
onto artificial intelligence for students
December 3, 2018 12:47 PM
Scoop.it!

Interpretability and performance: Can the same model achieve both?

Interpretability and performance: Can the same model achieve both? | artificial intelligence for students | Scoop.it
Interpretability and performance of a system are usually at odds with each other, as many of the best-performing models (viz. deep neural networks) are black box in nature. In our work, Improving Simple Models with Confidence Profiles, we try to bridge this gap by proposing a method to transfer information from a high-performing neural network to another model that the domain expert or the application may demand. For example, in computational biology and economics, sparse linear models are often preferred, while in complex instrumented domains such as semi-conductor manufacturing, the engineers might prefer using decision trees. Such simpler interpretable models can build trust with the expert and provide useful insight leading to discovery of novel and previously unknown facts. Our goal is pictorially depicted below, for a specific case in which we are trying to improve performance of a decision tree.
No comment yet.
artificial intelligence for students
artificial intelligence for students - postgraduate and undergraduate
Curated by Scott Turner