Muhammad Sabih

Has grant

Researcher

Fraunhofer Institute for Integrated Circuits
Country flagGermany

Research Interests

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Recent Grants

Grant: Open

Digital Signal Processing Using Generative Artificial Intelligence (DSgenAI)

Open Date: 2025-01-01

Close Date: 2028-12-01

Grant: Open

Open-Source Design Tools for the Co-Development of AI Algorithms and AI Chips (DI-EDAI)

Open Date: 2024-05-01

Close Date: 2027-04-01

Grant: Open

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

Open Date: 2024-05-01

Close Date: 2027-04-01

Grant: Close

AI Laboratory for System-level Design of ML-based Signal Processing Applications (KISS)

Open Date: 2019-10-01

Close Date: 2022-01-01

Articles (8)

Year:

2026

Year:

2025

Year:

2025

Year:

2025

Year:

2024

Filter pruning of convolutional neural networks (CNNs) is a common technique to effectively reduce the memory footprint, the number of arithmetic operations, and, consequently, inference time. Recent pruning approaches also consider the targeted device (i.e., graphics processing units) for CNN deployment to reduce the actual inference time. However, simple metrics, such as the $$\ell ^1$$ ℓ 1 -norm, are used for deciding which filters to prune. In this work, we propose a hardware-aware technique to explore the vast multi-objective design space of possible filter pruning configurations. Our approach incorporates not only the targeted device but also techniques from explainable artificial intelligence for ranking and deciding which filters to prune. For each layer, the number of filters to be pruned is optimized with the objective of minimizing the inference time and the error rate of the CNN. Experimental results show that our approach can speed up inference time by 1.40× and 1.30× for VGG-16 on the CIFAR-10 dataset and ResNet-18 on the ILSVRC-2012 dataset, respectively, compared to the state-of-the-art ABCPruner.

Year:

2024

Year:

2024

Year:

2023

Collaborators (3)

Vincent Meyers

Karlsruhe Institute of Technology

GERMANY
View details

Mehdi Tahoori

Professor and Chair

Karlsruher Institut für Technologie

GERMANY
View details

Jürgen Becker

Professor

Karlsruhe Institute of Technology

GERMANY
View details