Icing on the Cake: An Easy and Quick Post-Learnig Method You Can Try After Deep Learning

2018/07/17 by Konno, Tomohiko, Iwazume, Michiaki
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.1807.06540

Abstract

We found an easy and quick post-learning method named "Icing on the Cake" to enhance a classification performance in deep learning. The method is that we train only the final classifier again after an ordinary training is done.

Related

• Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
• Post Training in Deep Learning with Last Kernel
• Learning to Generate Synthetic Training Data using Gradient Matching and Implicit Differentiation
• Forward Thinking: Building and Training Neural Networks One Layer at a Time
• Improving Deep Learning through Automatic Programming