Search Results - "KAMAL, MEHDI"

Reliable yet high-speed memristor-based mixed-signal coarse-grained reconfigurable architecture for CNN inference acceleration.

Authors: Kazerooni-Zand, Reza Afzali-Kusha, Ali Kamal, Mehdi

Source: Neurocomputing; Aug2026, Vol. 688, pN.PAG-N.PAG, 1p

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.

Subjects: Artificial neural networks, Knowledge transfer, Power resources

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.

Subjects: Energy consumption, Radio frequency

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.

Subjects: Internet of things, Cloud storage, Distillation

An Adaptive Memory-Side Encryption Method for Improving Security and Lifetime of PCM-Based Main Memory.

Authors: Soltani, Morteza Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: IEEE Transactions on Computer-Aided Design of Integrated Circuits & Systems. Jun2022, Vol. 41 Issue 6, p1744-1756. 13p.

Subjects: Phase change memory, Recurrent neural networks, Memory, Random access memory

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.

Subjects: Mathematical analysis, Circuit elements, Cost functions, Memristors, Artificial neural networks

Geographic Terms: California

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.

Subjects: Circuit elements, Energy consumption, Artificial neural networks

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

Impact of Process Variations on Speedup and Maximum Achievable Frequency of Extensible Processors.

Authors: KAMAL, MEHDI AFZALI-KUSHA, ALI SAFARI, SAEED et al.

Source: ACM Journal on Emerging Technologies in Computing Systems; Apr2014, Vol. 10 Issue 3, p19:1-19:25, 25p

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.

Subjects: Cache memory, Multicore processors, Heuristic algorithms, Energy consumption, Multiprocessors

Circuit-Level Techniques for Logic and Memory Blocks in Approximate Computing Systemsx.

Authors: Amanollahi, Saba Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: Proceedings of the IEEE. Dec2020, Vol. 108 Issue 12, p2150-2177. 28p.

Subjects: Nonvolatile memory, Data warehousing, Memory, Random access memory, Cloud storage

X-CGRA: An Energy-Efficient Approximate Coarse-Grained Reconfigurable Architecture.

Authors: Akbari, Omid Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: IEEE Transactions on Computer-Aided Design of Integrated Circuits & Systems. Sep2020, Vol. 39 Issue 10, p2558-2571. 14p.

Subjects: Video processing, Energy consumption, Signal processing, Quality of service

O⁴-DNN: A Hybrid DSP-LUT-Based Processing Unit With Operation Packing and Out-of-Order Execution for Efficient Realization of Convolutional Neural Networks on FPGA Devices.

Authors: Haghi, Pouya Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: IEEE Transactions on Circuits & Systems. Part I: Regular Papers. Sep2020, Vol. 67 Issue 9, p3056-3069. 14p.

Subjects: Convolutional neural networks, Field programmable gate arrays, Artificial neural networks, Energy consumption

Interstice: Inverter-Based Memristive Neural Networks Discretization for Function Approximation Applications.

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

Source: IEEE Transactions on Very Large Scale Integration (VLSI) Systems. Jul2020, Vol. 28 Issue 7, p1578-1588. 11p.

Subjects: Electric inverters, Analog-to-digital converters, Circuit elements

RandShift: An Energy-Efficient Fault-Tolerant Method in Secure Nonvolatile Main Memory.

Authors: Soltani, Morteza Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: IEEE Transactions on Very Large Scale Integration (VLSI) Systems. Jan2020, Vol. 28 Issue 1, p287-291. 5p.

Subjects: Nonvolatile memory, Advanced Encryption Standard, Bit error rate, Cryptography, Random access memory, Error correction (Information theory), Fault location (Engineering), Error rates

DART: A Framework for Determining Approximation Levels in an Approximable Memory Hierarchy.

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

Source: IEEE Transactions on Very Large Scale Integration (VLSI) Systems. Jan2020, Vol. 28 Issue 1, p273-286. 14p.

Subjects: Dynamic random access memory, Signal-to-noise ratio, Cache memory, Memory, Random access memory, Computer systems

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

Res-DNN: A Residue Number System-Based DNN Accelerator Unit.

Authors: Samimi, Nasim Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: IEEE Transactions on Circuits & Systems. Part I: Regular Papers. Feb2020, Vol. 67 Issue 2, p658-671. 14p.

Subjects: Binary number system, Number systems, Energy consumption

TOSAM: An Energy-Efficient Truncation- and Rounding-Based Scalable Approximate Multiplier.

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

Source: IEEE Transactions on Very Large Scale Integration (VLSI) Systems. May2019, Vol. 27 Issue 5, p1161-1173. 13p.

Subjects: Multipliers (Mathematical analysis), Odd numbers, Energy consumption, Gaussian distribution, Multiplication, JPEG (Image coding standard)

Approximate Reverse Carry Propagate Adder for Energy-Efficient DSP Applications.

Authors: Pashaeifar, Masoud Kamal, Mehdi Afzali-Kusha, Ali et al.

Source: IEEE Transactions on Very Large Scale Integration (VLSI) Systems. Nov2018, Vol. 26 Issue 11, p2530-2541. 12p.

Subjects: Adders (Digital electronics), Digital signal processing, Electric power consumption, Discrete cosine transforms, Finite impulse response filters