219 citations · 249 across the 14 of their papers we have counts for
4 papers · 1 filter
Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimes
Julius Martinetz, Christoph Linse, Thomas Martinetz
We investigate the learning dynamics of classifiers in scenarios where classes are separable or classifiers are over-parameterized. In both cases, Empirical Risk Minimization (ERM)…
Do highly over-parameterized neural networks generalize since bad solutions are rare?
Julius Martinetz, Thomas Martinetz
We study over-parameterized classifiers where Empirical Risk Minimization (ERM) for learning leads to zero training error. In these over-parameterized settings there are many globa…
Solving Raven's Progressive Matrices with Multi-Layer Relation Networks
Marius Jahrens, Thomas Martinetz
Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine lea…
Multi-layer Relation Networks
Marius Jahrens, Thomas Martinetz
Relational Networks (RN) as introduced by Santoro et al. (2017) have demonstrated strong relational reasoning capabilities with a rather shallow architecture. Its single-layer desi…