Semi-supervised Feature Transfer

Semi-supervised Feature Transfer: The Practical Benefit of Deep Learning Today? Previous post Next post            Tweet Tags: API, Deep Learning, indico, Machine Learning, scikit-learn, Sentiment Analysis This post evaluates four different strategies for solving a problem with machine learning, where customized models built from semi-supervised “deep” features using transfer learning outperform models built from scratch, and rival state-of-the-art methods. By Daniel Kuster, indico. What is transfer learning? Transfer learning is the concept of training a model to solve one problem, and then using the knowledge it learned to help solve other problems. In practice, we pre-train a deep neural network using large datasets (many millions of examples), so that it learns generally useful feature representations. We can then copy those internal feature representations into new models, effectively transferring…


Link to Full Article: Semi-supervised Feature Transfer