Applications of Convolutional Neural Networks (CNNs)

Let us look into some examples of CNNs and understand why CNNs work well.

More examples of deep networks

We have demonstrated the CNN\text{CNN} on the classic MNIST\text{MNIST} dataset, but it’s interesting to note that these networks gained wide recognition in another dataset called ImageNet\text{ImageNet}. ImageNet\text{ImageNet} is a collection of over one\text{one} million pictures from the Internet that have been labeled for over 1,000\text{1,000} classes. This dataset has been used for a competition where some traditional machine learning methods such as SVMs have gained some success. However, the traditional methods stagnated, with accuracies remaining around 80\text{80} percent. Alex Krizhevsky and colleagues applied CNNs\text{CNNs} to the problem and won a competition in 2012, starting a trend of improving the performance of models in object recognition even further.

Get hands-on with 1200+ tech skills courses.