21 Mar 2017 Table of contents: Transfer Learning - Machine Learning's Next Frontier What is Transfer Learning? Why Transfer Learning Now? A Denition of Transfer Learning Transfer Learning Scenarios Applications of Transfer Learning Learning from simulations Adapting to new domains Transferring knowledge across languages Transfer Learning Methods Using pre-trained CNN features Learning domain-invariant representations Making representations more similar Confusing domains Related Research Areas In recent years, we have become increasingly good at training deep neural networks to learn a very accurate mapping from inputs to outputs, whether they are images, sentences, label predictions, etc. from large amounts of labeled data. What our models still frightfully lack is the ability to generalize to conditions that are dierent from the ones encountered during training. When is this necessary? Every time you apply your model not to a carefully constructed dataset bu
