This is the comparative study on convolution neural networks and deep neural networks on fashion mnist dataset. This data set contains a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes.
we can achieve more accuracy on training and testing datasets using convolutional neural networks than deep neural networks. there are multiple reasons are there to justify that CNN is better than dnn while classifying images.
The below picture shows a CNN sequence to classify a handwritten digit.
Here's an example of how the data looks when plotted.
A Convolutional Neural Network (ConvNet/CNN) is a Deep Learning algorithm that can take in an input image, assign importance (learnable weights and biases) to various aspects/objects in the image and be able to differentiate one from the other. The pre-processing required in a ConvNet is much lower as compared to other classification algorithms. While in primitive methods filters are hand-engineered, with enough training, ConvNets have the ability to learn these filters/characteristics.
To explore more on CNN's refer to this website: click here
Refer this for further visualization: kaggle