How are convolutional networks better than simple neural networks (Feed-forward networks)? Is the convolution operation the only difference between convolutional neural networks and deep networks?
Solved – Advantages of convolutional neural networks over “simple” feed-forward networks
conv-neural-networkdeep learningneural networks
Related Question
- Solved – Delimitation: feed forward- and radial basis networks
- Solved – the difference between convolutional neural networks and deep learning
- Solved – Convolution operator in CNN and how it differs from feed forward NN operation
- Solved – Why are nonlinear activations used in convolutional neural networks
Best Answer
Any time that you can legitimately make stronger assumptions, you can obtain stronger results. Convolutional networks make the assumption of locality, and hence are more powerful. This depends on data that in fact exhibits locality (autocorrelation) like images or time series.
Intuitively, if you are looking at an image, pixels in a region of the image are more likely to be related than pixels far away. So you can save a lot of neuron wiring if you don't (directly) wire distant pixels to the same neuron. With less wiring, you have more data per coefficient, which speeds things up and makes for better results.