AleXNet is a deep convolutional neural network that was trained on a large dataset(Image Net) to classify the 1. 2 million high-resolution images with 1000 different classes(Alex Krizhevsky and et al, 2017), in the current study, our data sets were employed on Alexnet by using transfer learning where consider transfer learning is an efficient and powerful solution for many classification problems. Training requires enough data and computer time, but much less than training from scratch (see Figure 2 for a comparison with pre-trained networks and training from scratch) (Bengio, 2012), and the result is a network specifically tailored to our objectives. It is beneficial that we use the pre-trained AlexNet architecture to build the network † where Figure 4 shows the AlexNet architecture.
AleXNet
is a deep convolutional neural
network
that
was trained
on a large dataset(Image Net) to classify the 1. 2 million high-resolution images with 1000
different
classes(Alex
Krizhevsky
and
et al
, 2017), in the
current
study, our data sets
were employed
on
Alexnet
by using transfer learning where consider transfer learning is an efficient and powerful solution for
many
classification problems. Training requires
enough
data and computer time,
but
much less than training from scratch (
see
Figure 2 for a comparison with pre-trained
networks
and training from scratch) (
Bengio
, 2012), and the result is a
network
specifically
tailored to our objectives. It is beneficial that we
use
the pre-trained
AlexNet
architecture to build the
network
† where Figure 4
shows
the
AlexNet
architecture.