Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Efficient Compilation and Mapping of Fixed Function Combinational Logic onto Digital Signal Processors Targeting Neural Network Inference and Utilizing High-level Synthesis


Jul 30, 2022
Soheil Nazar Shahsavani, Arash Fayyazi, Mahdi Nazemi, Massoud Pedram

* 25 page, 10 figures. Under review 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Sparse Periodic Systolic Dataflow for Lowering Latency and Power Dissipation of Convolutional Neural Network Accelerators


Jun 30, 2022
Jung Hwan Heo, Arash Fayyazi, Amirhossein Esmaili, Massoud Pedram

* 6 pages, Published in ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED) 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness


Mar 28, 2022
Souvik Kundu, Sairam Sundaresan, Massoud Pedram, Peter A. Beerel

* 14 pages, 10 figures, 1 table 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratch


Dec 24, 2021
Souvik Kundu, Shikai Wang, Qirui Sun, Peter A. Beerel, Massoud Pedram

* 4 pages, 2 figures, 2 tables 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards Low-Latency Energy-Efficient Deep SNNs via Attention-Guided Compression


Jul 16, 2021
Souvik Kundu, Gourav Datta, Massoud Pedram, Peter A. Beerel

* 10 Pages, 8 Figures, 5 Tables 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

NullaNet Tiny: Ultra-low-latency DNN Inference Through Fixed-function Combinational Logic


Apr 07, 2021
Mahdi Nazemi, Arash Fayyazi, Amirhossein Esmaili, Atharva Khare, Soheil Nazar Shahsavani, Massoud Pedram


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A2P-MANN: Adaptive Attention Inference Hops Pruned Memory-Augmented Neural Networks


Jan 24, 2021
Mohsen Ahmadzadeh, Mehdi Kamal, Ali Afzali-Kusha, Massoud Pedram

* 10 pages, 9 figures, 3 tables 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

BRDS: An FPGA-based LSTM Accelerator with Row-Balanced Dual-Ratio Sparsification


Jan 07, 2021
Seyed Abolfazl Ghasemzadeh, Erfan Bank Tavakoli, Mehdi Kamal, Ali Afzali-Kusha, Massoud Pedram

* 8 pages, 9 figures, 2 tables 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNs


Nov 03, 2020
Souvik Kundu, Mahdi Nazemi, Peter A. Beerel, Massoud Pedram

* 8 pages, 4 figures, conference paper 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

SynergicLearning: Neural Network-Based Feature Extraction for Highly-Accurate Hyperdimensional Learning


Aug 04, 2020
Mahdi Nazemi, Amirhossein Esmaili, Arash Fayyazi, Massoud Pedram


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>