3 papers
cs.LG2026
Flat Channels to Infinity in Neural Loss Landscapes
Flavio Martinelli, Alexander Van Meegen, Berfin ÅimÅek +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…
cs.AI2025
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…
cs.LG2025
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…