Zero-Shot Learning with Semantic Output Codes

Mark Palatucci, Dean Pomerleau, Geoffrey Hinton, and Tom Mitchell
Neural Information Processing Systems (NIPS), December, 2009.

  • Adobe portable document format (pdf) (190KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

We consider the problem of zero-shot learning, where the goal is to learn a classifier f: X -> Y that must predict novel values of Y that were omitted from the training set. To achieve this, we define the notion of a semantic output code classifier (SOC) which utilizes a knowledge base of semantic properties of Y to extrapolate to novel classes. We provide a formalism for this type of classifier and study its theoretical properties in a PAC framework, showing conditions under which the classifier can accurately predict novel classes. As a case study, we build a SOC classifier for a neural decoding task and show that it can often predict words that people are thinking about from functional magnetic resonance images (fMRI) of their neural activity, even without training examples for those words.

machine learning, fMRI, pattern recognition, brain-computer-interfaces


Text Reference
Mark Palatucci, Dean Pomerleau, Geoffrey Hinton, and Tom Mitchell, "Zero-Shot Learning with Semantic Output Codes," Neural Information Processing Systems (NIPS), December, 2009.

BibTeX Reference
   author = "Mark Palatucci and Dean Pomerleau and Geoffrey Hinton and Tom Mitchell",
   title = "Zero-Shot Learning with Semantic Output Codes",
   booktitle = "Neural Information Processing Systems (NIPS)",
   month = "December",
   year = "2009",