A framework for selecting deep learning hyper-parameters
O'Donoghue, Jim and Roantree, Mark
(2015)
A framework for selecting deep learning hyper-parameters.
In: 30th British International Conference on Databases, 6--8 July 2015, Edinburgh, Scotland.
ISBN 978-3-319-20423-9
Recent research has found that deep learning architectures show significant improvements over traditional shallow algorithms when mining high dimensional datasets. When the choice of algorithm employed, hyper-parameter setting, number of hidden layers and nodes within a layer are combined, the identification of an optimal configuration can be a lengthy process. Our work provides a framework for building deep learning architectures via a stepwise approach, together with an evaluation methodology to quickly identify poorly performing architectural configurations. Using a dataset with high dimensionality, we illustrate how different architectures perform and how one algorithm configuration can provide input for fine-tuning more complex models.