Transfer learning aims to test how well a deep learning system can solve problems similar to the ones it's already studied. For example, researchers might take a program that was trained to ...

In an industry first, deep transfer learning has now been used to train an artificial neural network to classify galaxies as spiral or elliptical with 99.8% accuracy based on their pictures.

Six in one Example tumour segmentations predicted by the deep transfer learning approach, for prostate cancer, lung cancer, melanoma, lymphoma, head-and-neck cancer and breast cancer (showing pre- and ...

A novel image-based deep learning approach achieves high accuracy and interpretability, offering potential for clinical ...

We hear a lot about surface to deep learning. In this blog, Peter DeWitt explains the different between the two citing a recently released paper by John Hattie and Gregory Donoghue which explores ...

Douglas Fisher, Nancy Frey, Adeyemi Stembridge, Todd Finley, Kenneth Baum, and David Krulwich share their ideas on transfer of learning.