no code implementations • 20 Oct 2017 • Arash Shahriari
A common practice in most of deep convolutional neural architectures is to employ fully-connected layers followed by Softmax activation to minimize cross-entropy loss for the sake of classification.
no code implementations • 20 Oct 2017 • Arash Shahriari
The reconstruction of the original wiring for the target domain is a heavy burden due to the size of interconnections across neurons.
no code implementations • 20 Oct 2017 • Arash Shahriari, Fatih Porikli
We propose a novel pooling strategy that learns how to adaptively rank deep convolutional features for selecting more informative representations.
no code implementations • 24 Jun 2016 • Arash Shahriari
Pruning of redundant or irrelevant instances of data is a key to every successful solution for pattern recognition.