Arash Ardakani

40 papers A* 3A 2C 5Misc 1Journal 18Unranked 11
YearRankTypeTitle / Venue / Authors
2025 — conf
DEMOTIC: A Differentiable Sampler for Multi-Level Digital Circuits.
ASP-DAC
Arash Ardakani, Minwoo Kang, Kevin He, Qijing Huang, Vighnesh M. Iyer, Suhong Moon, John Wawrzynek
2025 J jnl
DEMOTIC: A Differentiable Sampler for Multi-Level Digital Circuits.
CoRR
Arash Ardakani, Minwoo Kang, Kevin He, Qijing Huang, Vighnesh M. Iyer, Suhong Moon, John Wawrzynek
2025 A conf
High-Throughput SAT Sampling.
DATE
Arash Ardakani, Minwoo Kang, Kevin He, Qijing Huang, John Wawrzynek
2025 J jnl
High-Throughput SAT Sampling.
CoRR
Arash Ardakani, Minwoo Kang, Kevin He, Qijing Huang, John Wawrzynek
2025 — conf
Recurrent CircuitSAT Sampling for Sequential Circuits.
MLCAD
Arash Ardakani, Kevin He, John Wawrzynek
2025 J jnl
Recurrent CircuitSAT Sampling for Sequential Circuits.
CoRR
Arash Ardakani, Kevin He, John Wawrzynek
2024 A* conf
Late Breaking Results: Differential and Massively Parallel Sampling of SAT Formulas.
DAC
Arash Ardakani, Minwoo Kang, Kevin He, Vighnesh M. Iyer, Suhong Moon, John Wawrzynek
2024 — conf
SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics.
NAACL-HLT
Arash Ardakani, Altan Haan, Shangyin Tan, Doru-Thom Popovici, Alvin Cheung, Costin Iancu, Koushik Sen
2023 J jnl
SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics.
CoRR
Arash Ardakani, Altan Haan, Shangyin Tan, Doru-Thom Popovici, Alvin Cheung, Costin Iancu, Koushik Sen
2022 — conf
Partially-Random Initialization: A Smoking Gun for Binarization Hypothesis of BERT.
EMNLP (Findings)
Arash Ardakani
2022 J jnl
Standard Deviation-Based Quantization for Deep Neural Networks.
CoRR
Amir Ardakani, Arash Ardakani, Brett H. Meyer, James J. Clark, Warren J. Gross
2021 — conf
Fault-Tolerance of Binarized and Stochastic Computing-based Neural Networks.
SiPS
Amir Ardakani, Arash Ardakani, Warren J. Gross
2021 J jnl
Hardware-Aware Design for Edge Intelligence.
IEEE Open J. Circuits Syst.
Warren J. Gross, Brett H. Meyer, Arash Ardakani
2021 J jnl
Training Binarized Neural Networks Using Ternary Multipliers.
IEEE Des. Test
Amir Ardakani, Arash Ardakani, Warren J. Gross
2020 C conf
A Regression-Based Method to Synthesize Complex Arithmetic Computations on Stochastic Streams.
ISCAS
Arash Ardakani, Amir Ardakani, Warren J. Gross
2020 J jnl
Fast and Efficient Convolutional Accelerator for Edge Computing.
IEEE Trans. Computers
Arash Ardakani, Carlo Condo, Warren J. Gross
2020 A* conf
Training Linear Finite-State Machines.
NeurIPS
Arash Ardakani, Amir Ardakani, Warren J. Gross
2019 J jnl
Design and Implementation of a Polar Codes Blind Detection Scheme.
IEEE Trans. Circuits Syst. II Express Briefs
Carlo Condo, Seyyed Ali Hashemi, Arash Ardakani, Furkan Ercan, Warren J. Gross
2019 — conf
Learning Recurrent Binary/Ternary Weights.
ICLR (Poster)
Arash Ardakani, Zhengyun Ji, Sean C. Smithson, Brett H. Meyer, Warren J. Gross
2019 A conf
Learning to Skip Ineffectual Recurrent Computations in LSTMs.
DATE
Arash Ardakani, Zhengyun Ji, Warren J. Gross
2019 A* conf
The Synthesis of XNOR Recurrent Neural Networks with Stochastic Logic.
NeurIPS
Arash Ardakani, Zhengyun Ji, Amir Ardakani, Warren J. Gross
2018 C conf
A Convolutional Accelerator for Neural Networks With Binary Weights.
ISCAS
Arash Ardakani, Carlo Condo, Warren J. Gross
2018 — conf
A Multi-Mode Accelerator for Pruned Deep Neural Networks.
NEWCAS
Arash Ardakani, Carlo Condo, Warren J. Gross
2018 J jnl
An Architecture to Accelerate Convolution in Deep Neural Networks.
IEEE Trans. Circuits Syst. I Regul. Pap.
Arash Ardakani, Carlo Condo, Mehdi Ahmadi, Warren J. Gross
2018 J jnl
Design and Implementation of a Polar Codes Blind Detection Scheme.
CoRR
Carlo Condo, Seyyed Ali Hashemi, Arash Ardakani, Furkan Ercan, Warren J. Gross
2018 J jnl
Learning Recurrent Binary/Ternary Weights.
CoRR
Arash Ardakani, Zhengyun Ji, Sean C. Smithson, Brett H. Meyer, Warren J. Gross
2018 J jnl
Learning to Skip Ineffectual Recurrent Computations in LSTMs.
CoRR
Arash Ardakani, Zhengyun Ji, Warren J. Gross
2017 C conf
A low-complexity fully scalable interleaver/address generator based on a novel property of QPP interleavers.
ISCAS
Arash Ardakani, Mahdi Shabany
2017 — conf
Activation pruning of deep convolutional neural networks.
GlobalSIP
Arash Ardakani, Carlo Condo, Warren J. Gross
2017 J jnl
Multi-Mode Inference Engine for Convolutional Neural Networks.
CoRR
Arash Ardakani, Carlo Condo, Warren J. Gross
2017 — conf
Sparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of Deep Neural Networks.
ICLR (Poster)
Arash Ardakani, Carlo Condo, Warren J. Gross
2017 J jnl
VLSI Implementation of Deep Neural Network Using Integral Stochastic Computing.
IEEE Trans. Very Large Scale Integr. Syst.
Arash Ardakani, François Leduc-Primeau, Naoya Onizawa, Takahiro Hanyu, Warren J. Gross
2016 Misc conf
Hardware implementation of FIR/IIR digital filters using integral stochastic computation.
ICASSP
Arash Ardakani, François Leduc-Primeau, Warren J. Gross
2016 J jnl
Sparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of Deep Neural Networks.
CoRR
Arash Ardakani, Carlo Condo, Warren J. Gross
2016 — conf
Stochastic Computing Can Improve Upon Digital Spiking Neural Networks.
SiPS
Sean C. Smithson, Kaushik Boga, Arash Ardakani, Brett H. Meyer, Warren J. Gross
2016 — conf
VLSI implementation of deep neural networks using integral stochastic computing.
ISTC
Arash Ardakani, François Leduc-Primeau, Naoya Onizawa, Takahiro Hanyu, Warren J. Gross
2015 J jnl
A Novel Area-Efficient VLSI Architecture for Recursion Computation in LTE Turbo Decoders.
IEEE Trans. Circuits Syst. II Express Briefs
Arash Ardakani, Mahdi Shabany
2015 C conf
An efficient max-log MAP algorithm for VLSI implementation of turbo decoders.
ISCAS
Arash Ardakani, Mahdi Shabany
2015 J jnl
VLSI Implementation of Deep Neural Network Using Integral Stochastic Computing.
CoRR
Arash Ardakani, François Leduc-Primeau, Naoya Onizawa, Takahiro Hanyu, Warren J. Gross
2013 C conf
An efficient VLSI architecture of QPP interleaver/deinterleaver for LTE turbo coding.
ISCAS
Arash Ardakani, Mojtaba Mahdavi, Mahdi Shabany