Neural Approximate Accelerator Architecture Optimization for DNN Inference on Lightweight FPGAs (NA³Os)

Third party funded individual grant

Acronym: NA³Os

Start date : 01.05.2024

End date : 30.04.2027

Overview

Publications

(9)

External partners

(1)

Co-Design of CNN Accelerators for TinyML using Approximate Matrix Decomposition (2026) Hernandez Morales JJ, Mentzos G, Hannig F, Balaskas K, Zervakis G, Henkel J, Teich J Other publication type Dynamically Adaptable Ensemble Proxies for Training-Free Neural Architecture Search (2026) Heidorn C, Herderich T, Teich J Conference contribution, Conference Contribution A SIMD MAC RISC-V Extension with Approximate Multipliers for Accelerating CNN Inference in Tiny Embedded Devices (2025) Hernandez Morales JJ, Hannig F, Teich J Conference contribution, Original article Beyond BNNs: Design and Acceleration of Sub-Bit Neural Networks using RISC-V Custom Functional Units (2025) Sabih M, Abdo M, Hannig F, Teich J Journal article, Original article On-Device Training of Fully Quantized Deep Neural Networks on Cortex-M Microcontrollers (2024) Deutel M, Hannig F, Mutschler C, Teich J Journal article, Original article Accelerating DNNs using Weight Clustering on RISC-V Custom Functional Units (2024) Sabih M, Sesli B, Hannig F, Teich J Conference contribution, Conference Contribution Hardware/Software Co-Design of RISC-V Extensions for Accelerating Sparse DNNs on FPGAs (2024) Sabih M, Karim A, Wittmann J, Hannig F, Teich J Conference contribution, Conference Contribution Robust and Tiny Binary Neural Networks using Gradient-based Explainability Methods (2023) Sabih M, Yayla M, Hannig F, Teich J, Chen JJ Conference contribution, Conference Contribution Fault-Tolerant Low-Precision DNNs using Explainable AI (2021) Sabih M, Hannig F, Teich J Conference contribution, Conference Contribution