Generative Neural Networks Explained

Armando Vieira 2016-08-12 Armando Vieira 2016-08-12 Deep generative models are a powerful approach to unsupervised and semi-supervised learning where the goal is to discover the hidden structure within data without relying on external labels. Traditional Machine Learning (ML) is mostly discriminative – the goal being to discover a map from inputs to outputs, like image pixels to object names presented in it. These models, however, have several limitations: i) they require vast amounts of annotated data; ii) can fail drastically when presented with inputs very different from the training set; and iii) they can be intentionally subverted by humans or other ML algorithms and misclassify data – quite common in security and privacy protection, an area heavily relying on ML. Generative ML models, on the other hand, learn in a…


Link to Full Article: Generative Neural Networks Explained