27–29 May 2026
CERN
Europe/Zurich timezone
There is a live webcast for this event.
Ask questions on discord: https://cern.ch/fdf-qa

MONO: Enhancing Bit-Flip Resilience With Bit Homogeneity for Neural Networks

27 May 2026, 19:22
1m
500/1-001 - Main Auditorium (CERN)

500/1-001 - Main Auditorium

CERN

400
Show room on map
Poster Solutions to everyday digital design problems Poster Session and Welcome Reception

Speaker

Maryam Eslami (Ruhr-Universität Bochum)

Description

Deep neural networks (DNNs) have been applied across diverse domains, including safety-critical applications. Past studies indicate that DNNs are very sensitive to changes in weights and activations due to uneven bit-weight distribution in standard number formats like fixed points, which can cause significant output accuracy fluctuations. To address this issue, we introduce a new data type called MONO to enhance bit flip resilience using uniformity at the bit level by employing symmetric weights for all bit positions. On average, MONO has improved error resilience more effectively than the fixed-point data type, even when utilizing triple modular redundancy (TMR) and most significant bit (MSB) protection, while maintaining low overhead.

Talk's Q&A During the talk
Talk duration 15'+7'
Will you be able to present in person? No
If we are unable to accommodate your oral presentation, would you be willing to consider presenting a poster instead? Yes

Author

Maryam Eslami (Ruhr-Universität Bochum)

Co-authors

Prof. Akash Kumar Dr Salim Ullah Mr Yuhao Liu

Presentation materials