Convolution Neural Networks by Image Net
Journal Title: International journal of Emerging Trends in Science and Technology - Year 2017, Vol 4, Issue 9
Abstract
We trained a large, deep convolution neural network to classify the 1.2 million high-resolution images in the Image Net LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolution layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way soft ax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called ―dropout‖ that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry
Authors and Affiliations
Dr. K. Vikram
A University Model Thesis on Globalization for Globalism
Research for fulfilling the needs and expectations of Society at large , as a matter of fact , becomes Policy of Quality and Equality in thinking and activities of contemporary Researchers. One such area of Research with...
Gravity, Quantum Mysteries and Einstein’s Last Dream
Einstein‟s General theory of relativity is an excellent theory of gravity but it is still a classical theory. In this paper after giving a broad overview of Gravity, I will use Quantum Field Theory and Graviton to show t...
Assessment of Regulatory Compliances in Diagnostic X-ray Facilities in Tangail District, Bangladesh
Due to increasing public demand, diagnostic x-ray facilities are expanding from the city to district even at rural areas faster than ever before in Bangladesh. At the same time radiological safety issues are also becomin...
Design and Implementation of Health Monitoring System by Using RF Communication
Health plays a crucial role in our life. The main aim of this project is to implement the system which keeps on monitoring the patient and saves him in the case of emergency Wireless communication system is designed and...
A Review Paper on Arithmetic and Logical Unit for Graphics Processor
In this era of high end devices, the power efficient architecture is taking responsibility so as to reduce the cost for maintenance. This becomes the critical task for embedded based device, graphical based processor and...