A number of recent deep learning techniques have been proposed that extend the core ideas of deep learning to new applications and learning scenarios. In this section, we will cover two such models that have gained prominence recently.
Recent models for deep learning
Generative Adversarial Networks
Recently, one popular field of machine learning that has seen the use of deep learning techniques is generative learning. Generative learning can be defined as a technique for learning joint probability estimates, P(x,y) from features and labels. It builds a probabilistic model of labels and can be robust to missing data and noisy data. Additionally, such models can also be used to generate samples, which can be further used to...
