Search Results - "PEDRAM, MASSOUD"

On the use of approximate computing for improving the robustness of DNNs against adversarial attacks.

Authors: Divsalar, Sahand Arezoomand, Fatemeh Vahdat, Shaghayegh et al.

Source: Journal of Supercomputing; Feb2026, Vol. 82 Issue 3, p1-27, 27p

Coarse2Fine: a two-stage training method for fine-grained visual classification.

Authors: Eshratifar, Amir Erfan Eigen, David Gormish, Michael et al.

Source: Machine Vision & Applications; 2021, Vol. 32 Issue 2, p1-9, 9p

AFMIS: An approximate floating-point multiplier based on input segmentation.

Authors: Naseri Rad, Asma Vahdat, Shaghayegh Afzali-Kusha, Ali et al.

Source: Future Generation Computer Systems; Jul2026, Vol. 180, pN.PAG-N.PAG, 1p

Toward Adversary-aware Non-iterative Model Pruning through Dynamic Network Rewiring of DNNs.

Authors: SOUVIK KUNDU YAO FU BILL YE et al.

Source: ACM Transactions on Embedded Computing Systems; Sep2022, Vol. 21 Issue 5, p1-24, 24p

qSeq: Full Algorithmic and Tool Support for Synthesizing Sequential Circuits in Superconducting SFQ Technology.

Authors: Pasandi, Ghasem Pedram, Massoud

Source: DAC: Annual ACM/IEEE Design Automation Conference; 2021, Issue 58, p133-138, 6p

Federated learning by employing knowledge distillation on edge devices with limited hardware resources.

Authors: Tanghatari, Ehsan Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: Neurocomputing; Apr2023, Vol. 531, p87-99, 13p

TDP-ADMM: A Timing Driven Placement Approach for Superconductive Electronic Circuits Using Alternating Direction Method of Multipliers.

Authors: Shahsavani, Soheil Nazar Pedram, Massoud

Source: DAC: Annual ACM/IEEE Design Automation Conference; 2020, Issue 57, p746-751, 6p

Depth-bounded Graph Partitioning Algorithm and Dual Clocking Method for Realization of Superconducting SFQ Circuits.

Authors: PASANDI, GHASEM PEDRAM, MASSOUD

Source: ACM Journal on Emerging Technologies in Computing Systems; Oct2020, Vol. 17 Issue 1, p1-22, 22p

Internal write‐back and read‐before‐write schemes to eliminate the disturbance to the half‐selected cells in SRAMs.

Authors: Pasandi, Ghasem Pedram, Massoud

Source: IET Circuits, Devices & Systems (Wiley-Blackwell); Jul2018, Vol. 12 Issue 4, p460-466, 7p

Posit Process Element for Using in Energy-Efficient DNN Accelerators.

Authors: Zolfagharinejad, Mohamadreza Kamal, Mehdi Afzali-Khusha, Ali et al.

Source: IEEE Transactions on Very Large Scale Integration (VLSI) Systems; Jun2022, Vol. 30 Issue 6, p844-848, 5p

High-Radix Design of a Scalable Montgomery Modular Multiplier With Low Latency.

Authors: Zhang, Bo Cheng, Zeming Pedram, Massoud

Source: IEEE Transactions on Computers; Feb2022, Vol. 71 Issue 2, p436-449, 14p

Distributing DNN training over IoT edge devices based on transfer learning.

Authors: Tanghatari, Ehsan Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: Neurocomputing; Jan2022, Vol. 467, p56-65, 10p

A Logic Verification Framework for SFQ and AQFP Superconducting Circuits.

Authors: Fayyazi, Arash Munir, Mustafa Gopikanna, Aswin et al.

Source: IEEE Transactions on Applied Superconductivity; Dec2021, Vol. 31 Issue 9, p1-11, 11p

LATIM: Loading-Aware Offline Training Method for Inverter-Based Memristive Neural Networks.

Authors: Vahdat, Shaghayegh Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: IEEE Transactions on Circuits & Systems. Part II: Express Briefs; Oct2021, Vol. 68 Issue 10, p3346-3350, 5p

An 8-b Multiplier Using Single-Stage Full Adder Cell in Single-Flux-Quantum Circuit Technology.

Authors: Cong, Haolin Li, Mingye Pedram, Massoud

Source: IEEE Transactions on Applied Superconductivity; Sep2021, Vol. 31 Issue 6, p1-10, 10p

Reliability Enhancement of Inverter-Based Memristor Crossbar Neural Networks Using Mathematical Analysis of Circuit Non-Idealities.

Authors: Vahdat, Shaghayegh Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: IEEE Transactions on Circuits & Systems. Part I: Regular Papers; Oct2021, Vol. 68 Issue 10, p4310-4323, 14p

Loading-Aware Reliability Improvement of Ultra-Low Power Memristive Neural Networks.

Authors: Vahdat, Shaghayegh Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: IEEE Transactions on Circuits & Systems. Part I: Regular Papers; Aug2021, Vol. 68 Issue 8, p3411-3421, 11p

JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services.

Authors: Eshratifar, Amir Erfan Abrishami, Mohammad Saeed Pedram, Massoud

Source: IEEE Transactions on Mobile Computing; Feb2021, Vol. 20 Issue 2, p565-576, 12p

OPTIMA: An Approach for Online Management of Cache Approximation Levels in Approximate Processing Systems.

Authors: Yarmand, Roohollah Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: IEEE Transactions on Very Large Scale Integration (VLSI) Systems; Feb2021, Vol. 29 Issue 2, p434-446, 13p

Offline Training Improvement of Inverter-Based Memristive Neural Networks Using Inverter Voltage Characteristic Smoothing.

Authors: Vahdat, Shaghayegh Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: IEEE Transactions on Circuits & Systems. Part II: Express Briefs; Dec2020, Vol. 67 Issue 12, p3442-3446, 5p