Help us make Indico better by taking this survey! Aidez-nous à améliorer Indico en répondant à ce sondage !

Sep 25 – 28, 2023
Imperial College London
Europe/London timezone

FKeras: A Sensitivity Analysis Tool for Edge Neural Networks

Sep 27, 2023, 2:30 PM
15m
Blackett Laboratory, Lecture Theatre 1 (Imperial College London)

Blackett Laboratory, Lecture Theatre 1

Imperial College London

Blackett Laboratory
Standard Talk Contributed Talks Contributed Talks

Speaker

Olivia Weng

Description

Scientific experiments rely on machine learning at the edge to process extreme volumes of real-time streaming data. Extreme edge computation often requires robustness to faults, e.g., to function correctly in high radiation environments or to reduce the effects of transient errors. As such, the computation must be designed with fault tolerance as a primary objective. FKeras is a tool that assesses the sensitivity of machine learning parameters to faults. FKeras uses a metric based on the Hessian of the neural network loss function to provide a bit-level ranking of neural network parameters with respect to their sensitivity to transient faults. FKeras is a valuable tool for the co-design of robust and fast ML algorithms. It guides and accelerates fault injection campaigns for single and multiple-bit flip error models. It analyzes the resilience of a neural network under single and multiple bit-flip fault models. It helps evaluate the fault tolerance of a network architecture, enabling co-design that considers fault tolerance alongside performance, power, and area. By quickly identifying the sensitive parameters, FKeras can determine how to protect neural network parameters selectively.

Primary author

Co-authors

Abarajithan G (UC San Diego) Andres Meza (UC San Diego) Ben Hawks (Fermi National Accelerator Lab) Christopher Crutchfield (UC San Diego) Javier Campos Javier Mauricio Duarte (Univ. of California San Diego (US)) Nhan Tran (Fermi National Accelerator Lab. (US)) Quinlan Bock (Fermilab) Ryan Kastner

Presentation materials