An interesting article I thought might end up being relevant to deep learning research…
https://www.sciencedaily.com/releases/2017/06/170612094100.htm
When the researchers presented the virtual brain tissue with a stimulus, cliques of progressively higher dimensions assembled momentarily to enclose high-dimensional holes, that the researchers refer to as cavities. “The appearance of high-dimensional cavities when the brain is processing information means that the neurons in the network react to stimuli in an extremely organized manner,” says Levi. “It is as if the brain reacts to a stimulus by building then razing a tower of multi-dimensional blocks, starting with rods (1D), then planks (2D), then cubes (3D), and then more complex geometries with 4D, 5D, etc. The progression of activity through the brain resembles a multi-dimensional sandcastle that materializes out of the sand and then disintegrates.”
These higher dimensional spaces sound a lot like embedding spaces to my ear. The momentary nature of the structures used to create these embeddings is an interesting concept. I’m not sure that there’s an equivalent in deep learning, but I thought it was interesting and wanted to hear others thoughts.