If you just have a single problem to solve then fine go ahead and use a neural network. But if you want to do science and understand how to choose architectures or how to go to a new problem you have to understand what different architectures can and cannot do.
It turns out that understanding the British public is not rocket science. The British appreciate honesty and they also have a bonkers off-the-wall sense of humour like me.
Next Article
From my earliest acquaintance with the science of political economy it has been evident to my mind that capital was the product of labor and that therefore in its best analysis there could be no natural conflict between capital and labor.
