{"id":248,"date":"2022-02-02T15:18:08","date_gmt":"2022-02-02T14:18:08","guid":{"rendered":"https:\/\/machinelearning.humanativaspa.it\/en\/?p=248"},"modified":"2023-03-03T14:58:27","modified_gmt":"2023-03-03T13:58:27","slug":"feed-forward-neural-networks-cnn-convolutional-neural-network","status":"publish","type":"post","link":"https:\/\/machinelearning.humanativaspa.it\/en\/feed-forward-neural-networks-cnn-convolutional-neural-network\/","title":{"rendered":"Feed-forward neural networks -CNN – convolutional neural network"},"content":{"rendered":"

\u00a0<\/span>In the previous article we described in general the functioning of neural networks, in this second publication we will analyze in detail the “Convolutional Neural Network” (CNN), a type of feed-forward neural networks.<\/span>\u00a0<\/span><\/p>\n

Convolutional neural networks are born from studies conducted on animal prefrontal cortices and have been used in image recognition processes since 1980.<\/span>\u00a0<\/span><\/p>\n

In the CCNs, filters are applied that recognize particular correlations or patterns within the image itself, in order to generate optimal features to be supplied as input to a neural network (usually fully-connected).<\/span>\u00a0<\/span><\/p>\n

From the mathematical point of view, the convolution operation consists in “multiplying” two matrices suitably translated to calculate the result, one of which represents the image being analyzed and the other the filter that is applied.<\/span>\u00a0<\/span><\/p>\n

With convolution operations it is possible, in fact, to apply specific filters to extract a set of information. For example, in image recognition you could extract the left edges with the first filter, the right ones with the second, the corners with the third etc. … until the optimum accuracy level is reached.<\/span>\u00a0<\/span><\/p>\n

In the process of convolution, we have three fundamental elements:<\/span>\u00a0<\/span><\/p>\n