Search Results for: Reduced size models
a wide range of models, including deep learning models, but also pro- vide an easy-to-use, efficient and effective service for users without much machine learning knowledge and experience, e.g., database users. considering that different models may result in different performance in terms of efficiency
(e.g., latency) and effectiveness (e.g., accuracy), the cloud service has to select the proper models for a given task. moreover, most machine learning models and the training algorithms come with a set of hyper-parameters or knobs, e.g., number of layers and size of each layer in a neural network....
http://www.vldb.org/pvldb/vol12/p128-wang.pdf