MSMuhammad Sabih

Muhammad Sabih

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Muhammad Sabih has a total of 32 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Beyond BNNs: Design and Acceleration of Sub-Bit Neural Networks Using RISC-V Custom Functional Units

    by Muhammad Sabih, Mohamed Abdo, Frank Hannig, Jürgen Teich

    Binary neural networks (BNNs) are known for their minimal memory requirements, making them an attractive choice for resource-constrained environments. SBNN-nps are a more recent advancement that extend the benefits of BNNs by compressing them even further, achieving sub-bit level representations to maximize efficiency. However, effectively compressing and accelerating BNNs presents challenges. In this letter, we propose a novel approach to compress BNNs using a fixed-length compression scheme that can be efficiently decoded at runtime. We then propose RISC-V extensions, implemented as a custom function unit (CFU), to decode compressed weights via a codebook stored on an FPGA on-board memory, followed by XOR and population count operations. This approach achieves a speedup of up to 2× compared to conventional BNNs deployed on the RISC-V softcore, with Significantly less accuracy degradation, and provides a foundation for exploring even higher compression configurations to improve performance further.


  • Open Access

    Special Sessions - Hardware-Software Co-Design for Machine Learning Systems Made Open-Source

    by Mehdi Tahoori, Vincent Meyers, Mahboobe Sadeghipour Roodsari, Huashuangyang Xu, Juergen Becker, Tanja Harbaum, Felix Frombach, Julian Hoefer, Georgios Sotiropoulos, Jorg Henkel, et al.


  • Open Access

    Hardware-Aware Evolutionary Explainable Filter Pruning for Convolutional Neural Networks

    by Christian Heidorn, Muhammad Sabih, Nicolai Meyerhöfer, Christian Schinabeck, Jürgen Teich, Frank Hannig

    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.


  • Open Access

    Robust and Tiny Binary Neural Networks using Gradient-based Explainability Methods

    by Muhammad Sabih, Mikail Yayla, Frank Hannig, Jürgen Teich, Jian-Jia Chen

    Binary neural networks (BNNs) are a highly resource-efficient variant of neural networks. The efficiency of BNNs for tiny machine learning (TinyML) systems can be enhanced by structured pruning and making BNNs robust to faults. When used with approximate memory systems, this fault tolerance can be traded off for energy consumption, latency, or cost. For pruning, magnitude-based heuristics are not useful because the weights in a BNN can either be -1 or +1. Global pruning of BNNs has not been studied well so far. Thus, in this paper, we explore gradient-based ranking criteria for pruning BNNs and use them in combination with a sensitivity analysis. For robustness, the state-of-the-art is to train the BNNs with bit-flips in what is known as fault-aware training. We propose a method to guide fault-aware training using gradient-based explainability methods. This allows us to obtain robust and efficient BNNs for deployment on tiny devices. Experiments on audio and image processing applications show that our proposed approach outperforms the existing approaches, making it useful for obtaining efficient and robust models for a slight degradation in accuracy. This makes our approach valuable for many TinyML use cases.