What is dimension hopping problem in machine learning (or convolutional neural networks or image recognition)? I have google about it but all I get is Physics of material shape deformation. It will be more helpful if some one explain it with example.

What is the dimension hopping problem in machine learning (occurring in convolutional neural networks and image recognition)? I have googled about it but all I get is information on the Physics of material shape deformation. It will be more helpful to me if some one explain it with an example related to machine learning. Can anyone help me out with this or point me toward resources that can?