Open AccessIneffectual Neuron Free Deep Learning Accelerator
Author(s) -
B. Nikhita Tanvi,
Maria Azees,
Gayathri Suresh
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.i8664.078919
Subject(s) - computer science , convolutional neural network , compiler , deep learning , pooling , computation , artificial intelligence , computational complexity theory , parallel computing , algorithm , programming language
Convolutional neural network (CNN) is actually a deep neural network which plays an important role in image recognition. The CNN recognizes images similar to visual cortex in our eyes. In this proposed work, an accelerator is used for high efficient convolutional computations. The main aim of using the accelerator is to avoid ineffectusal computations and to improve performance and energy efficiency during image recognition without any loss in accuracy. However, the throughput of the accelerator is improved by adding max-pooling function only. Since the CNN includes multiple inputs and intermediate weights for its convolutional computation, the computational complexity is increased enormously. Hence, to reduce the computational complexity of the CNN, a CNN accelerator is proposed in this paper. The accelerator design is simulated and synthesized in Cadence RTL compiler tool with 90nm technology library.