Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
This paper investigates the trade-off between structured pruning and fault tolerance in DNNs for space applications by systematically reducing model width via structured pruning and evaluating robustness to Single Event Upsets (SEUs) through targeted fault injection. The study reveals that while pruning reduces inherent redundancy, the resulting shorter inference times decrease the probability of SEU occurrence, effectively counterbalancing the increased per-inference sensitivity. Consequently, structured pruning offers a viable path to energy and latency savings without sacrificing overall reliability in fault-prone environments.
Structured pruning can slash DNN energy and latency for space applications without sacrificing reliability, by trading redundancy for reduced SEU probability.
Deep Neural Networks (DNNs) inherently exhibit a degree of robustness to bit-level faults due to their distributed representation of information. As a model increases in width, this information becomes more dispersed, theoretically reducing the impact of any single bit fault. In this paper, we empirically investigate the relationship between model width and robustness to Single Event Upsets (SEUs). We conduct a comprehensive experiment in which baseline models undergo iterative structured pruning to reduce their width while preserving task performance as much as possible. At each pruning stage, we run a targeted fault-injection campaign to evaluate the model's performance under simulated bit-flip scenarios. Our results show that, although structured pruning increases per-inference sensitivity to faults by reducing redundancy, this effect is effectively counterbalanced by shorter execution time, which lowers the probability of encountering an SEU. These findings suggest that structured pruning can yield significant energy and latency savings without compromising overall reliability, providing useful guidance for designing robust AI systems for space applications.