{"id":5542,"date":"2021-05-07T10:36:27","date_gmt":"2021-05-07T08:36:27","guid":{"rendered":"https:\/\/joapen.com\/blog\/?p=5542"},"modified":"2021-05-07T11:05:53","modified_gmt":"2021-05-07T09:05:53","slug":"notes-about-convolutional-neural-networks","status":"publish","type":"post","link":"http:\/\/joapen.com\/blog\/2021\/05\/07\/notes-about-convolutional-neural-networks\/","title":{"rendered":"Notes about convolutional neural networks"},"content":{"rendered":"\n

Let’s start with Wikipedia<\/a>: In deep learning, a convolutional neural network (CNN, or ConvNet) is a class of deep neural network, most commonly applied to analyze visual imagery<\/strong>.<\/p>\n\n\n\n

The name \u201cconvolutional neural network\u201d indicates that the network employs a mathematical operation called convolution<\/strong>. The convolutional networks are a specialized type of neural networks that use convolution in place of general matrix multiplication in at least one of their layers.<\/p>\n\n\n\n

Representation of the matrix multiplication in one layer:<\/h3>\n\n\n\n
\"matrix
matrix multiplication in one layer for a convolution neural network<\/figcaption><\/figure><\/div>\n\n\n\n

A convolutional neural network processes data that has a grid-like arrangement then extracts important features. One huge advantage of using CNNs is that you don’t need to do a lot of pre-processing on images.<\/p>\n\n\n\n

\"A
A vanilla Convolutional Neural Network (CNN) representation<\/figcaption><\/figure>\n\n\n\n

A basic clasiffication of CNNs is by number of dimensions:<\/h3>\n\n\n\n