International Journal of Advance Research and Innovation



Yüklə 0,71 Mb.
Pdf görüntüsü
səhifə3/13
tarix27.01.2023
ölçüsü0,71 Mb.
#81145
1   2   3   4   5   6   7   8   9   ...   13
IJARI-ME-14-09-106 (1)

Corresponding Author, 
E-mail address: ranganathdce@gmail.com 
All rights reserved: http://www.ijari.org 
the crematorium. This problem was shorted out by 
Wolfgang Scheffler who invented a new concentrator 
(scheffler reflector) tracking the Sun without changing it 
focus. In this paper, scheffler reflector is redesigned to 
determine required size (Aperture Area) of the concentrator 
to obtain sufficient heat energy for cremating a corpse. 
2. Artificial Neural Network
Neural network is one of the important components in 
Artificial Intelligence (AI). It has been studied for many 
years in the hope of achieving human-like performance in 
many fields, such as speech and image recognition as well 
as information retrieval. A Neural Network is an 
interconnected assembly of simple processing elements, 
units or nodes, whose functionality is loosely based on the 
animal neuron. The processing ability of the network is 
stored in the inter-unit connection strengths, or weights, 
obtained by a process of adaptation to, or learning from, a 
set of training patterns. In its most general form, a neural 
network is a machine that is designed to model the way in 
which the brain performs a particular task or function of 
interest; the network is usually implemented by using 
electronic components or is simulated in software on a 
digital computer. A neural network is a parallel distributed 
processor made up of simple processing units, which has a 
natural propensity for storing experiential knowledge and 
making it available for use. It resembles the brain in two 
respects: Knowledge is acquired by the network from its 
environment through a learning process; Interneuron 
connection strengths, known as synaptic weights, are used 
to store the acquired knowledge. In summary, neural 
networks are models attempt to achieve good performance 
via dense interconnection of simple computational elements. 
A neural network has three components: a network, an 
activation rule, and a learning rule. The network consists of 

Yüklə 0,71 Mb.

Dostları ilə paylaş:
1   2   3   4   5   6   7   8   9   ...   13




Verilənlər bazası müəlliflik hüququ ilə müdafiə olunur ©www.azkurs.org 2024
rəhbərliyinə müraciət

gir | qeydiyyatdan keç
    Ana səhifə


yükləyin