Neither Quick Nor Proper -- Evaluation of QuickProp for Learning Deep Neural Networks

06/14/2016
by   Clemens-Alexander Brust, et al.
0

Neural networks and especially convolutional neural networks are of great interest in current computer vision research. However, many techniques, extensions, and modifications have been published in the past, which are not yet used by current approaches. In this paper, we study the application of a method called QuickProp for training of deep neural networks. In particular, we apply QuickProp during learning and testing of fully convolutional networks for the task of semantic segmentation. We compare QuickProp empirically with gradient descent, which is the current standard method. Experiments suggest that QuickProp can not compete with standard gradient descent techniques for complex computer vision tasks like semantic segmentation.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset