کنفرانس مهندسی برق ایران

صفحه اصلی / بیست و نهمین کنفرانس مهندسی برق ایران

A Fast Approach for Deep Neural Network Implementation on FPGA

نویسندگان :

Maedeh Nobari¹ Hadi Jahanirad²

1- دانشگاه کردستان 2- دانشگاه کردستان

کلمات کلیدی :

.(Artificial Neural Network (ANN), Stochastic computing (SC), Field-Programmable Gate Array (FPGA), Probability Estimator (PE

چکیده :

Stochastic computing (SC) has received tremendous attentions for implementation of artificial neural networks (ANN). The hardware complexity of such an implementation is significantly reduced in comparison with conventional counterpart. One of major problems regarding the SC implementation of ANN is its slow convergence rate. Millions of clocks are required to generate a fairly accurate output by a single neuron. In this paper, a novel approach is developed in which the results of stochastic operations are determined after a specific clock cycle. The proper handshaking signaling are utilized among the interconnected neurons to interchange the necessary information. The proposed architecture is implemented on Virtex7 FPGA. The simulation results show a great improvement in accuracy along with significant speed up.

لیست مقالات

لیست مقالات بایگانی شده

تخمین پارامتر سری‌های زمانی دو بعدی چند متغیره گسسته

مرضیه بهمنی - محسن شفیعی‌راد - مهدی زینالی - احسان ناظم‌الرعایا

ساخت یک تراشه میکروسیالی برای شمارش سلول های معلق در مایع با الکترود های مایع

نرگس حسین زاده - پادینا فرخیان - سیدعلی حسینی

Total Transfer Capability Improvement Using High Temperature Low Sag Conductors

Seyed Sina Mousavi-Seyedi - Mohammad Reza Rezaei - Mohammad Reza Miveh

Multi-Objective Concurrent Kernel Scheduling for Multi-GPU Systems

Negar Baradar Alizadeh - Mahmoud Momtazpour

Modeling and control of two PPR cooperative manipulations with a passive joint

Hassan Khosravi - Farhad Fani Saberi - Rasul Fesharakifard

طراحی و شبیه سازی شتاب سنج خازنی MEMS برای استفاده در سمعک های تمام کاشت

میلاد کریمی پور - مهدیه مهران

Multi-Agent Systems for Quadcopter under Nonlinear Dynamics and Actuator Modeling with MPC and LQR Controller

Navid Mohammadi - Saeed Khankalantary

Development of Reflectarray Antennas With a Deflected Beam: An Approach Based on Artificial Neural Networks

Mahdieh Esmaeiliporzani - Zahra Atlasbaf

40Hz Auditory Entrainment Promotes Synchronization Between Frontal and Parietal Regions of the Brain

Mojtaba Lahijanian - Hamid Aghajan

Modeling the Cable Bridge Based on Two Dimensional System and Analysing the Stability of Desired Model Based on Wave Advanced Model

Mehdi Mirshahi - Masoud Shafiee - Mehdi Mohammadi

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2