Learning a manifold from a teacher’s demonstrationsDownload PDF

Oct 10, 2020 (edited Dec 07, 2020)NeurIPS 2020 Workshop TDA and Beyond Blind SubmissionReaders: Everyone
  • Keywords: manifold learning, machine teaching
  • TL;DR: We consider the problem of learning the topology of a manifold from a teacher’s demonstration.
  • Abstract: We consider the problem of learning a manifold from a teacher's demonstration. Extending existing approaches of learning from randomly sampled data points, we consider contexts where data may be chosen by a teacher. We analyze learning from teachers who can provide structured data such as individual examples (isolated data points) and demonstrations (sequences of points). Our analysis shows that for the purpose of teaching the topology of a manifold, demonstrations can yield remarkable decreases in the amount of data points required in comparison to teaching with randomly sampled points.
  • Previous Submission: No
  • Poster: pdf
1 Reply