Please wait ...
0% Complete
Home
/
12th International Conference on Computer and Knowledge Engineering
Low-Cost and Hardware Efficient Implementation of Pooling Layers for Stochastic CNN Accelerators
Authors :
Mobin Vaziri
1
Hadi Jahanirad
2
1- University of Kurdistan
2- University of Kurdistan
Keywords :
Convolutional neural networks،Stochastic computing،Pooling layers،High-level synthesis tools
Abstract :
With the astonishing achievements of Convolutional Neural Network (CNN) accelerators in real-time applications, the deployment of CNNs on hardware has become an attractive matter. Pooling layers in CNNs are employed for reducing the computation of convolutional layers. Nevertheless, their hardware implementation strategy can impact the accuracy and performance of accelerators. This paper presents a novel parallel Stochastic Computing (SC) based architecture of pooling modules in hardware for stochastic CNN accelerators. With this approach, the SC-based average pooling is reconfigurable with 1.28 times lower power consumption, and the max pooling layer achieves area reduction with the ratio of 4.36. Increasing the accuracy and extending the application of stochastic CNN accelerators in different classification problems is also achieved by implementing AAD pooling with the proposed method.
Papers List
List of archived papers
ExaASC: A General Target-Based Stance Detection Corpus in Arabic Language
Mohammad Mehdi Jaziriyan - Ahmad Akbari - Hamed Karbasi
A Facial Deepfake Detection Approach using CNN-based Models, Swin Transformer and Classifier Fusion
Alireza Honardoost - Mahdie Rahmati - Babak Nasersharif
Intelligent Interpretation of Frequency Response Signatures to Diagnose Radial Deformation in Transformer Windings Using Artificial Neural Network
Reza Behkam - Hossein Karami - Mehdi Salay Naderi - Gevork B. Gharehpetian
Paddy Plant Stress Identification Using Few-Shot Learning Framework
Ervin Gubin Moung - Pavindrah Naidu a/l Narayanasamy Naiidu - Maisarah Mohd Sufian - Valentino Liaw - Ali Farzamnia - Lorita Angeline
A Genetic-based Fusion Approach of Persian and Universal Phonetic results for Spoken Language Identification
Ashkan Moradi - Yasser Shekofteh - Saeed Zarei
Efficient T-Count Fault-tolerant Quantum Clifford+T Multiplexer
Negin Mashayekhi - Shekoofeh Moghimi - Mohammad Reza Reshadinezhad
Attentional Bi-LSTM for Multivariate Time Series Forecasting on Edge Devices: A Case Study on NanoPi Neo Plus2
Navid Hajizadeh - Saeed Yazdani - Sara Ershadi-Nasab
SingAll: Scalable Control Flow Checking for Multi-Process Embedded Systems
Mehdi Amininasab - Ahmad Patooghy - Mahdi Fazeli
IR-LPR: Large Scale of Iranian License Plate Recognition Dataset
Mahdi Rahmani - Melika Sabaghian - Seyyedeh Mahila Moghadami - Mohammad Mohsen Talaie - Mahdi Naghibi - Mohammad Ali Keyvanrad
Investigation of topological characteristics of Iranian railway network: A network science approach
Sina Firuzbakht - Mohammad Khansari
more
Samin Hamayesh - Version 44.9.3