Search Results for author: Mikael Sjodin

Found 1 papers, 0 papers with code

DeepAxe: A Framework for Exploration of Approximation and Reliability Trade-offs in DNN Accelerators

no code implementations14 Mar 2023 Mahdi Taheri, Mohammad Riazati, Mohammad Hasan Ahmadilivani, Maksim Jenihhin, Masoud Daneshtalab, Jaan Raik, Mikael Sjodin, Bjorn Lisper

The framework enables selective approximation of reliability-critical DNNs, providing a set of Pareto-optimal DNN implementation design space points for the target resource utilization requirements.

Cannot find the paper you are looking for? You can Submit a new open access paper.