503 citations
- Google (United States)US2 papers
- Max Planck Institute for Dynamics and Self-OrganizationDE2 papers
- Max Planck SocietyDE2 papers
- Allen InstituteUS1 paper
- Allen Institute for Brain ScienceUS1 paper
- Bernstein Center for Computational Neuroscience GöttingenDE1 paper
- Georgian Technical UniversityGE1 paper
- Hebrew University of JerusalemIL1 paper
- Kent State UniversityUS1 paper
- Max Planck InnovationDE1 paper
- New York UniversityUS1 paper
- Pennsylvania State UniversityUS1 paper
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2019★ 33 cited
Understanding overfitting peaks in generalization error: Analytical risk curves for and penalized interpolation
Partha P Mitra
Traditionally in regression one minimizes the number of fitting parameters or uses smoothing/regularization to trade training (TE) and generalization error (GE). Driving TE to zero…
cs.LG2017★ 74 cited
Discovering objects and their relations from entangled scene representations
David Raposo, Adam Santoro, David Barrett +3
Our world can be succinctly and compactly described as structured scenes of objects and relations. A typical room, for example, contains salient objects such as tables, chairs and…