AlexNet was introduced in 2012 by Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton in a paper titled ImageNet Classification with Deep Convolutional Neural Networks. The original paper can be found at http://www.cs.utoronto.ca/~ilya/pubs/2012/imgnet.pdf.
It was the first successful introduction of an optimized CNN model to solve computer vision problems regarding the classification of a large number of images (over 15 million) from many different categories (over 22,000). Before AlexNet, computer vision problems were mainly solved by traditional machine learning methods, which made incremental improvements by collecting larger datasets and improving the model and techniques to minimize overfitting.
CNN models classify error rates in terms of a top-five error rate, which is the percentage of instances where the true class of a given image is not amongst...
