vjk

Great article - very inspiring to hear about his collaboration with another undergraduate at MIT over 3 years, and the joint awards they've won together.

My undergraduate graph theory textbook had this quote from Paul Erdos:

" Suppose aliens invade the earth and threaten to obliterate it in a year's time unless human beings can find the Ramsey number for red five and blue five. We could marshal the world's best minds and fastest computers, and within a year we could probably calculate the value.

If the aliens demanded the Ramsey number for red six and blue six, however, we would have no choice but to launch a preemptive attack."

In other words - some of the basic questions about these unbelievably small numbers (that you could count on your hands and toes) are so difficult, they push the limits of human ingenuity.

Great post! It was fun to see 4 tracks in the (first convolutional layer) filter 242 set that I recognized from my own 'ambient' Spotify playlists, and pretty impressive at the topmost layer as well. Loved that approach of looking at a few tracks that represented maximally or average activated filters.

Curious if you think the low-level features learned from the vector_exp latent factors are different from, say, unsupervised learning with sparse autoencoders? For example, are there phonemes associated with Chinese pop or Spanish rap that are learned at a low level, that the network might not learn with "unlabeled" data?