Alexnet Technology

Alexnet is the name given to a Convolutional Neural Network Architecture. Alexnet solves the problem of image classification with subset of ImageNet dataset with roughly 1.2 million training images, 50,000 validation images, and 150,000 testing images. The input is an image of one of 1000 different classes and output is a vector of 1000 numbers. The neural network, which has 60 million parameters and 650,000 neurons, consists of 5 convolutional layers, some of which are followed by max-pooling layers, and 3 fully connected layers. The unique advantage of AlexNet is the direct image input to the classification model. The results of AlexNet show that a large, deep convolutional neural network. It is capable of achieving record-breaking results on a highly challenging dataset using purely supervised learning. An important feature of the AlexNet is the use of ReLU(Rectified Linear Unit) Nonlinearity and a very efficient GPU implementation of the convolution operations. Alexnet Architecture employed regularization methods such as Dropout and Data Augmentation to reduce overfitting in the fully connected layers.