Mathematical Algorithm Design for Deep Learning under Societal and Judicial Constraints: The Algorithmic Transparency Requirement

no code implementations • 18 Jan 2024 • Holger Boche, Adalbert Fono, Gitta Kutyniok

Motivated by the observation that the current evolution of deep learning models necessitates a change in computing technology, we derive a mathematical framework which enables us to analyze whether a transparent implementation in a computing model is feasible.

Expressivity of Spiking Neural Networks

no code implementations • 16 Aug 2023 • Manjot Singh, Adalbert Fono, Gitta Kutyniok

The synergy between spiking neural networks and neuromorphic hardware holds promise for the development of energy-efficient AI applications.

Inverse Problems Are Solvable on Real Number Signal Processing Hardware

no code implementations • 5 Apr 2022 • Holger Boche, Adalbert Fono, Gitta Kutyniok

For this, we focus on the class of inverse problems, which, in particular, encompasses any task to reconstruct data from measurements.

Limitations of Deep Learning for Inverse Problems on Digital Hardware

no code implementations • 28 Feb 2022 • Holger Boche, Adalbert Fono, Gitta Kutyniok

Deep neural networks have seen tremendous success over the last years.