CONVOLUTIONAL NEURAL NETWORK (CNN)
Convolutional Neural Networks (CNNs), CNNs, also known as ConvNets, are multi-layer neural networks that are primarily used for image processing and object detection. Yann LeCun created the first CNN, known as LeNet, in 1988. It was used for character recognition, such as ZIP codes and digits. The figure above is an image processed via CNN. CNNs are widely used to identify satellite images, process medical images, forecast time series, and detect anomalies. CNNs works that have multiple layers that process and extract features from data: Convolution Layer - CNN has a convolution layer with several filters that performs convolution. Rectified Linear Unit (ReLU) - CNNs have a ReLU layer that allows them to perform operations on elements. The result is a feature map that has been rectified. Pooling Layer - The corrected feature map is then fed into a pooling layer. Pooling is a downsampling operation that reduces the dimensions of the feature map and the pooling layer then flattens the resulting two-dimensional arrays from the pooled feature map. Fully Connected Layer - When the flattened matrix from the pooling layer is fed as an input, a fully connected layer forms, which classifies and identifies the images.
Actually, I have explained about Convolutional Neural Network (CNN) to recognize handwritten digits, in this section. Then, now, we can practice more using another example algorithm.
In this tutorial, you'll learn how to use Keras to implement Convolutional Neural Networks (CNNs) and how to overcome overfitting with dropout. We will use The Fashion-MNIST Data Set. Before you begin loading data, it's a good idea to take a look at what you'll be working with! The Fashion-MNIST dataset contains 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set contains 60,000 images, while the test set contains 10,000 images. You can double-check this after you've loaded your data! ;) Fashion-MNIST is similar to the MNIST dataset, which you may be familiar with and use to classify handwritten digits. That is, the image dimensions, training and test splits are similar to those found in the MNIST dataset.
Full Convolutional Neural Networks using Fashion-MNIST data in Python with Keras
See the full code below, the code of CNN for Deep Learning using Fashion MNIST: