Bayesian representation learning with oracle constraints

Understand

Representation learning systems typically rely on massive amounts of labeled data in order to be trained to high accuracy.

• Recently, high-dimensional parametric models like neural networks have succeeded in building rich representations using either compressive, reconstructive or supervised criteria.
• However, the semantic structure inherent in observations is oftentimes lost in the process.
• Human perception excels at understanding semantics but cannot always be expressed in terms of labels.