Return to Answer

Auto-encoders

Auto-encoders are neural networks that compress the input and then decompress it. The answers to this question may help you to understand why AEs would be useful.

For example, a convolution neural network (CNN), provided it doesn't contain recurrent connections, is an FFNN that performs the convolution operation (and often also a sub-sampling operation). For this reason, they are particularly suited to deal with images (and videos). (This shouldn't be surprising if you are familiar with the basics of image processing and computer vision, which I don't think it's the case)

(You may hear people say that the CNN doesn't perform the convolution operation, but the cross-correlation, but this distinction is irrelevant in the case of CNNs, because the kernels are learned. Moreover, the convolution and cross-correlation are equivalent when the kernels are symmetric, e.g. when you use a Gaussian kernel).

For example, a convolution neural network (CNN), provided it doesn't contain recurrent connections, is an FFNN that performs the convolution operation (and often also a sub-sampling operation). For this reason, they are particularly suited to deal with images (and videos). (This shouldn't be surprising if you are familiar with the basics of image processing and computer vision, which I don't think it's the case)

• Weighted (i.e. binary, such as the McCulloch and Pitts' model) vs unweighted (e.g. the perceptron)
• Synchronous vs asynchronous (e.g. Hopfield networks, which are recurrent neural networks, though)
• Neural networks that store states vs NNs that don't store states

• Unweighted (i.e. binary, such as the McCulloch and Pitts' model) vs weighted (e.g. the perceptron)
• Synchronous vs asynchronous (e.g. Hopfield networks, which are recurrent neural networks, though)
• Neural networks that store states vs NNs that don't store states