- Abstract: Recent research in the deep learning field has produced a plethora of new architectures. At the same time, a growing number of groups are applying deep learning to new applications. Some of these groups are likely to be composed of inexperienced deep learning practitioners who are baffled by the dizzying array of architecture choices and therefore opt to use an older architecture (i.e., Alexnet). Here we attempt to bridge this gap by mining the collective knowledge contained in recent deep learning research to discover underlying principles for designing neural network architectures. In addition, we describe several architectural innovations, including Fractal of FractalNet network, Stagewise Boosting Networks, and Taylor Series Networks (our Caffe code and prototxt files are available at https://github.com/iPhysicist/CNNDesignPatterns). We hope others are inspired to build on our preliminary work.
- TL;DR: We take a high-level view of the network architectures as the basis for discovering universal principles of the design of convolutional neural network architecture..
- Conflicts: nrl.navy.mil, umbc.edu