29 citations · 45 across the 7 of their papers we have counts for
8 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…
Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks
Ann Huang, Satpreet H. Singh, Flavio Martinelli +1
Task-trained recurrent neural networks (RNNs) are widely used in neuroscience and machine learning to model dynamical computations. To gain mechanistic insight into how neural syst…
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…
MLPGradientFlow: going with the flow of multilayer perceptrons (and finding minima fast and accurately)
Johanni Brea, Flavio Martinelli, Berfin Şimşek +1
MLPGradientFlow is a software package to solve numerically the gradient flow differential equation , where are the parameters of a mu…
A Bin Encoding Training of a Spiking Neural Network-based Voice Activity Detection
Giorgia Dellaferrera, Flavio Martinelli, Milos Cernak
Advances of deep learning for Artificial Neural Networks(ANNs) have led to significant improvements in the performance of digital signal processing systems implemented on digital c…
Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection
Flavio Martinelli, Giorgia Dellaferrera, Pablo Mainar +1
Recent advances in Voice Activity Detection (VAD) are driven by artificial and Recurrent Neural Networks (RNNs), however, using a VAD system in battery-operated devices requires fu…