TY - GEN
T1 - A Mathematical Framework for Computability Aspects of Algorithmic Transparency
AU - Boche, Holger
AU - Fono, Adalbert
AU - Kutyniok, Gitta
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - The lack of trustworthiness is a major downside of deep learning. To mitigate the associated risks clear obligations of deep learning models have been proposed via regulatory guidelines. Therefore, a crucial question is to what extent trustworthy deep learning can be realized. Establishing trust-worthiness requires that the factors influencing an algorithmic computation can be retraced, i.e., the algorithmic implementation is transparent. Motivated by the observation that the current evolution of deep learning models necessitates a change in computing technology, we derive a mathematical framework that enables us to analyze whether a transparent implementation in a given computing model is feasible. We exemplarily apply our trustworthiness framework to analyze deep learning approaches for inverse problems in digital and analog computing models represented by Turing and Blum-Shub-Smale Machines, respectively. Based on previous results, we find that Blum-Shub-Smale Machines have the potential to establish trustworthy solvers for inverse problems under fairly general conditions, whereas, Turing machines cannot guarantee trustworthiness to the same degree. For a longer version of this paper with more details and proofs, we refer to [1].
AB - The lack of trustworthiness is a major downside of deep learning. To mitigate the associated risks clear obligations of deep learning models have been proposed via regulatory guidelines. Therefore, a crucial question is to what extent trustworthy deep learning can be realized. Establishing trust-worthiness requires that the factors influencing an algorithmic computation can be retraced, i.e., the algorithmic implementation is transparent. Motivated by the observation that the current evolution of deep learning models necessitates a change in computing technology, we derive a mathematical framework that enables us to analyze whether a transparent implementation in a given computing model is feasible. We exemplarily apply our trustworthiness framework to analyze deep learning approaches for inverse problems in digital and analog computing models represented by Turing and Blum-Shub-Smale Machines, respectively. Based on previous results, we find that Blum-Shub-Smale Machines have the potential to establish trustworthy solvers for inverse problems under fairly general conditions, whereas, Turing machines cannot guarantee trustworthiness to the same degree. For a longer version of this paper with more details and proofs, we refer to [1].
UR - http://www.scopus.com/inward/record.url?scp=85195833232&partnerID=8YFLogxK
U2 - 10.1109/ISIT57864.2024.10619190
DO - 10.1109/ISIT57864.2024.10619190
M3 - Conference contribution
AN - SCOPUS:85195833232
T3 - IEEE International Symposium on Information Theory - Proceedings
SP - 3089
EP - 3094
BT - 2024 IEEE International Symposium on Information Theory, ISIT 2024 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 IEEE International Symposium on Information Theory, ISIT 2024
Y2 - 7 July 2024 through 12 July 2024
ER -