In this article you will learn the detail architure of'AlexNet'. It was introduced in research paper ImageNet Classification with Deep Convolutional Neural Networks by Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton in year 2010. Before introducing AlexNet the labelled image dataset was relatively small like CIFAR and NORB consisting of tens of thousands of images. However, The recent availability of large datasets like ImageNet consist 15 million labelled high-resolution images belonging to roughly 22,000 categories pushed the demand of capable deep learning algorithm. In 2010 they started training a large deep convolutional neural network to classify the 1.2 million high resolution images from the ImageNet LSVRC into 1000 different classes. Before 2010 it was easy to train model on thousand images and detect the object in the image with a low resolution, but when applied to high-resolution it was very difficult to train.