Convolutional Neural Networks

The architecture behind

Neural Networks are a class of algorithms widely used in Deep Learning, the field of Machine Learning whose aim is that of learning data representation via multi-layers, deep algorithms.

So by definition, Neural Networks are made of multiple layers, each one approaching towards more meaningful insight of the input data (if you want to learn more about NNs, you can read my former article here).

Convolutional Neural Networks are nothing but Neural Networks that exhibit, in at least one layer, the mathematical operation of convolution. They are specialized in the field of Computer Vision and their main goal is that of dealing with images, to understand their inner structures, and address specific tasks (like image classification).

Convolution is an element-wise multiplication between two matrices (representing, respectively, a filter specialized in detecting specific features and an equally-sized region of the image being processed) with the final summation of the outputs. Let’s see how it works within the whole architecture of CNN. As such, they are linear operations.

The high-level architecture of a CNN is made of four main stages:

• Convolutional stage
• Detector stage