no code implementations • 10 Apr 2024 • Ahmed Agiza, Mohamed Mostagir, Sherief Reda
In an era where language models are increasingly integrated into decision-making and communication, understanding the biases within Large Language Models (LLMs) becomes imperative, especially when these models are applied in the economic and political domains.
1 code implementation • 29 Mar 2024 • Ahmed Agiza, Marina Neseem, Sherief Reda
Adapting models pre-trained on large-scale datasets to a variety of downstream tasks is a common strategy in deep learning.
no code implementations • 6 Feb 2024 • Abdelrahman Hosny, Sherief Reda
Then, we present a novel neural network architecture to model our differentiable function, and progressively solve MaxSAT using backpropagation.
no code implementations • 16 Sep 2023 • Manar Abdelatty, Joseph Incandela, Kangping Hu, Joseph W. Larkin, Sherief Reda, Jacob K. Rosenstein
Electrical capacitance tomography (ECT) is a nonoptical imaging technique in which a map of the interior permittivity of a volume is estimated by making capacitance measurements at its boundary and solving an inverse problem.
no code implementations • 7 Aug 2023 • Ahmed Agiza, Rajarshi Roy, Teodor Dumitru Ene, Saad Godil, Sherief Reda, Bryan Catanzaro
Given a gate-level netlist of a circuit represented as a graph, GraPhSyM utilizes graph structure, connectivity, and electrical property features to predict the impact of physical synthesis transformations such as buffer insertion and gate sizing.
no code implementations • 2 Jul 2023 • Abdelrahman Hosny, Sherief Reda
We show that instances that have similar costs using one solver configuration also have similar costs using another solver configuration in the same runtime environment.
1 code implementation • 17 Apr 2023 • Marina Neseem, Ahmed Agiza, Sherief Reda
Specifically, we attach a task-aware lightweight policy network to the shared encoder and co-train it alongside the MTL model to recognize unnecessary computations.
1 code implementation • 29 Oct 2021 • Abdelrahman Hosny, Marina Neseem, Sherief Reda
However, memory footprint from activations is the main bottleneck for training on the edge.
1 code implementation • 16 Aug 2021 • Marina Neseem, Sherief Reda
In particular, our technique clusters the object categories based on their spatial co-occurrence probability.
1 code implementation • 22 Feb 2021 • Abdelrahman Hosny, Sherief Reda
However, deploying EDA jobs on the cloud requires EDA teams to deeply understand the characteristics of their jobs in cloud environments.
no code implementations • 10 Jun 2020 • Marina Neseem, Jon Nelson, Sherief Reda
The proposed techniques reduce the power consumption by dynamically switching among different sensor configurations as a function of the user activity.
1 code implementation • 11 Nov 2019 • Abdelrahman Hosny, Soheil Hashemi, Mohamed Shalan, Sherief Reda
Logic synthesis requires extensive tuning of the synthesis optimization flow where the quality of results (QoR) depends on the sequence of optimizations used.
1 code implementation • 8 Sep 2019 • Hokchhay Tann, Heng Zhao, Sherief Reda
To attain accurate and efficient FCN models, we propose a three-step SW/HW co-design methodology consisting of FCN architectural exploration, precision quantization, and hardware acceleration.
no code implementations • 23 Jan 2018 • Hokchhay Tann, Soheil Hashemi, Sherief Reda
In addition, DNNs are typically deployed in ensemble to boost accuracy performance, which further exacerbates the system requirements.
no code implementations • 11 May 2017 • Hokchhay Tann, Soheil Hashemi, Iris Bahar, Sherief Reda
In addition, we propose a hardware accelerator design to achieve low-power, low-latency inference with insignificant degradation in accuracy.
no code implementations • 12 Dec 2016 • Soheil Hashemi, Nicholas Anthony, Hokchhay Tann, R. Iris Bahar, Sherief Reda
While a large number of dedicated hardware using different precisions has recently been proposed, there exists no comprehensive study of different bit precisions and arithmetic in both inputs and network parameters.
no code implementations • 19 Jul 2016 • Hokchhay Tann, Soheil Hashemi, R. Iris Bahar, Sherief Reda
We present a novel dynamic configuration technique for deep neural networks that permits step-wise energy-accuracy trade-offs during runtime.