305 citations · 611 across the 20 of their papers we have counts for
23 papers
Teacher Geometry Shapes Learnability in Teacher-Student Networks
Kai J. Sandbrink, Flavio Martinelli, Alexander van Meegen +2
Teacher-student systems, in which a teacher neural network generates training labels so that a student neural network can learn to implement the same function, are widely used as a…
Data Augmentation Techniques to Reverse-Engineer Neural Network Weights from Input-Output Queries
Alexander Beiser, Flavio Martinelli, Wulfram Gerstner +1
Network weights can be reverse-engineered given enough informative samples of a network's input-output function. In a teacher-student setup, this translates into collecting a datas…
Flat Channels to Infinity in Neural Loss Landscapes
Flavio Martinelli, Alexander Van Meegen, Berfin Şimşek +2
The loss landscapes of neural networks contain minima and saddle points that may be connected in flat regions or appear in isolation. We identify and characterize a special structu…
Should Under-parameterized Student Networks Copy or Average Teacher Weights?
Berfin Şimşek, Amire Bendjeddou, Wulfram Gerstner +1
Any continuous function can be approximated arbitrarily well by a neural network with sufficiently many neurons . We consider the case when itself is a neural networ…
Expand-and-Cluster: Parameter Recovery of Neural Networks
Flavio Martinelli, Berfin Simsek, Wulfram Gerstner +1
Can we identify the weights of a neural network by probing its input-output mapping? At first glance, this problem seems to have many solutions because of permutation, overparamete…
Emergent rate-based dynamics in duplicate-free populations of spiking neurons
Valentin Schmutz, Johanni Brea, Wulfram Gerstner
Can Spiking Neural Networks (SNNs) approximate the dynamics of Recurrent Neural Networks (RNNs)? Arguments in classical mean-field theory based on laws of large numbers provide a p…