Deep Convolutional Neural Network Design Patterns

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 is available at https://github.com/iPhysicist/CNNDesignPatterns). We hope others are inspired to build on our preliminary work.

Submitted as a conference paper at ICLR 2017

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Striving for Simplicity: The All Convolutional Net
• Residual Networks of Residual Networks: Multilevel Residual Networks
• Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning
• Understanding Locally Competitive Networks
• Convolutional Residual Memory Networks

Cited by in corpus (2)

• Revealing structure components of the retina by deep learning networks
• Neuron Segmentation Using Deep Complete Bipartite Networks