= Representation learning
<Representation learning> learns a transformation of observations into <feature (machine learning)>[features] that make a subsequent task easier. Writing $z=f_\theta(x)$ and a prediction as $g_\phi(z)$ separates the learned representation from the predictor; training may optimize both together. The objective can come from <supervised learning> or <unsupervised learning>.
For example, a <neural network> trained to classify images can learn edge-like and shape-sensitive <feature (machine learning)>[features] instead of receiving a fixed list of hand-measured quantities. The representation can sometimes be reused on a second task with fewer labeled examples. Such transfer is a hypothesis to evaluate: information useful for the original task can omit a distinction essential to the next. A <distributed representation> describes how information is encoded; <representation learning> describes how the encoding is obtained.<Deep Learning by Ian Goodfellow and others>[Chapter 15, opening discussion and transfer learning]{ref}
Back to article page
