Of course ! If you already get what neural networks are there is already a good answer from Borhan Kazimipour on ai.stackexchange.com : https://ai.stackexchange.com/questions/5546/what-is-the-difference-between-a-convolutional-neural-network-and-a-regular-neur?noredirect=1

It will tell you the difference between Neural Networks and Convolutional Neural Networks.

The best sentence to memorize is : "A convolution unit receives its input from multiple units from the previous layer which together create a proximity. " For instance, imagine you have an image of 256*256 pixels and you want to get some information about it (such as the probability to have a dog in the picture), you can divide it in a smaller number of neurons which will have some pixels as inputs and give a number as output (such as the probability to have a dog in the part they were in charge of).

I hope it will help you and remember that the best way to learn it it do it by yourself. Andrew Ng had great courses about it on Coursera.

Convolutional Neural Networks (CNNs / ConvNets)

Convolutional Neural Networks are very similar to ordinary Neural Networks from the previous chapter: they are made up of neurons that have learnable weights and biases. Each neuron receives some inputs, performs a dot product and optionally follows it with a non-linearity. The whole network still expresses a single differentiable score function: from the raw image pixels on one end to class scores at the other. And they still have a loss function (e.g. SVM/Softmax) on the last (fully-connected) layer and all the tips/tricks we developed for learning regular Neural Networks still apply.

So what does change? ConvNet architectures make the explicit assumption that the inputs are images, which allows us to encode certain properties into the architecture. These then make the forward function more efficient to implement and vastly reduce the amount of parameters in the network.

Architecture Overview

Recall: Regular Neural Nets. As we saw in the previous chapter, Neural Networks receive an input (a single vector), and transform it through a series of hidden layers. Each hidden layer is made up of a set of neurons, where each neuron is fully connected to all neurons in the previous layer, and where neurons in a single layer function completely independently and do not share any connections. The last fully-connected layer is called the “output layer” and in classification settings it represents the class scores.

Regular Neural Nets don’t scale well to full images. In CIFAR-10, images are only of size 32x32x3 (32 wide, 32 high, 3 color channels), so a single fully-connected neuron in a first hidden layer of a regular Neural Network would have 32*32*3 = 3072 weights. This amount still seems manageable, but clearly this fully-connected structure does not scale to larger images. For example, an image of more respectable size, e.g. 200x200x3, would lead to neurons that have 200*200*3 = 120,000 weights. Moreover, we would almost certainly want to have several such neurons, so the parameters would add up quickly! Clearly, this full connectivity is wasteful and the huge number of parameters would quickly lead to overfitting.

3D volumes of neurons. Convolutional Neural Networks take advantage of the fact that the input consists of images and they constrain the architecture in a more sensible way. In particular, unlike a regular Neural Network, the layers of a ConvNet have neurons arranged in 3 dimensions: width, height, depth. (Note that the word depthhere refers to the third dimension of an activation volume, not to the depth of a full Neural Network, which can refer to the total number of layers in a network.) For example, the input images in CIFAR-10 are an input volume of activations, and the volume has dimensions 32x32x3 (width, height, depth respectively). As we will soon see, the neurons in a layer will only be connected to a small region of the layer before it, instead of all of the neurons in a fully-connected manner. Moreover, the final output layer would for CIFAR-10 have dimensions 1x1x10, because by the end of the ConvNet architecture we will reduce the full image into a single vector of class scores, arranged along the depth dimension. Here is a visualization

http://cs231n.github.io/convolutional-networks/

regards

This link is useful

http://cs231n.github.io/convolutional-networks/

Regards

You can benefit from the following links:

http://www.mathworks.com/matlabcentral/fileexchange/24291-cnn-convolutional-neural-network-class

http://yann.lecun.com/exdb/lenet/ – A demonstration of a convolutional network created for character recognition

Interesting

thank u all for valuable answers

thank u dr Hassan for valuable answer.