LeCun tweeted here: https://twitter.com/ylecun/status/1209497021398343680?s=20, about what is the real definition of DL as he said “Some folks still seem confused about what deep learning is. Here is a definition: DL is constructing networks of parameterized functional modules & training them from examples using gradient-based optimization”

I think he is pointing to Gary Marques’debate with Bengio, and it seems controversial discussion over the thread, I don’t know what do you think about LeCun statement about DL definition.