To deal with small amount of training data with deep learning

Hi, I think major problem in this competition is a few training dataset compared to test dataset. I found some papers which deal with the problem, so I want to share with you. Dan C. Ciresan et.al. (2012), Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images, NIPS Olaf RonneBerger et.al. (2015), U-Net: Convolutional Networks for Biomedical Image Segmentation, arXiv 1505.04597 These papers deal with images segmentation problem in biological research where the number of images tends to be very few compared to the images used in other research areas. I think both papers utilising the uniformity of the image to expand the dataset. As you know, we augment dataset by cropping or rotating the images if data were like MNIST, but to preserve the meaning of the image…


Link to Full Article: To deal with small amount of training data with deep learning

Pin It on Pinterest

Share This

Join Our Newsletter

Sign up to our mailing list to receive the latest news and updates about homeAI.info and the Informed.AI Network of AI related websites which includes Events.AI, Neurons.AI, Awards.AI, and Vocation.AI

You have Successfully Subscribed!