Search Results for author: Malik Magdin-Ismail

Found 1 papers, 0 papers with code

Quantifying error contributions of computational steps, algorithms and hyperparameter choices in image classification pipelines

no code implementations25 Feb 2019 Aritra Chowdhury, Malik Magdin-Ismail, Bulent Yener

We show that algorithm selection and hyper-parameter optimization methods can be used to quantify the error contribution and that random search is able to quantify the contribution more accurately than Bayesian optimization.

Bayesian Optimization BIG-bench Machine Learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.