Interpretability of deep learning models: A survey of results.
Supriyo ChakrabortyRichard TomsettRamya RaghavendraDaniel HarborneMoustafa AlzantotFederico CeruttiMani B. SrivastavaAlun D. PreeceSimon JulierRaghuveer M. RaoTroy D. KelleyDave BrainesMurat SensoyChristopher J. WillisPrudhvi GurramPublished in: SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI (2017)
Keyphrases
- learning models
- learning tasks
- machine learning
- loss function
- learning algorithm
- classification models
- semi supervised learning
- machine learning algorithms
- learning paradigms
- learning problems
- conditional random fields
- machine learning models
- supervised learning
- probabilistic model
- learning process
- pairwise
- computer vision