9 papers
Equivalence of approximation by networks of single- and multi-spike neurons
Dominik Dold, Philipp Christian Petersen
In a spiking neural network, is it enough for each neuron to spike at most once? In recent work, approximation bounds for spiking neural networks have been derived, quantifying how…
Continuous Design and Reprogramming of Totimorphic Structures for Space Applications
Dominik Dold, Amy Thomas, Nicole Rosi +2
Recently, a class of mechanical lattices with reconfigurable, zero-stiffness structures has been proposed, called Totimorphic lattices. In this work, we introduce a computational f…
Reconfiguration of pivoting cube ensembles under local sensing constraints using geometric deep learning
Nadezhda Dobreva, Emmanuel Blazquez, Jai Grover +3
We demonstrate that local sensing is sufficient for effective global reconfiguration of homogeneous pivoting cube modular robots in two dimensions. While cube selection (i.e., whic…
Memristor-Based Neural Network Accelerators for Space Applications: Enhancing Performance with Temporal Averaging and SIRENs
Zacharia A. Rudge, Dominik Dold, Moritz Fieback +2
Memristors are an emerging technology that enables artificial intelligence (AI) accelerators with high energy efficiency and radiation robustness -- properties that are vital for t…
Guidance and Control Neural Network Acceleration using Memristors
Zacharia A. Rudge, Dario Izzo, Moritz Fieback +3
In recent years, the space community has been exploring the possibilities of Artificial Intelligence (AI), specifically Artificial Neural Networks (ANNs), for a variety of on board…
Stable Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders
A. Martina Neuman, Dominik Dold, Philipp Christian Petersen
We study the learning problem associated with spiking neural networks. Specifically, we focus on spiking neural networks composed of simple spiking neurons having only positive syn…