[rockmeamedee]

Hey I love this but watch out with this kind of stuff. And by stuff I mean training RNNs to do classification on very small (100s) sets of images. (Also you didn't mention your train/test split?). Which just means, get more data and make a smaller network by likely re-using a trained network.

I highly recommend the paper "Understanding deep learning requires rethinking generalization" (https://arxiv.org/abs/1611.03530), which shows how amazing some RNNs are at memorizing pure noise.

Would love to see different applications of DL on historical visual art: GANNs making new paintings in different styles, mapping meaning-space between artists, style transfer, "is this painting done by this artist?" ...

[s-shellfish]

Mapping meaning space sounds interesting. To me, art is a relation between myself, what is not myself, and how my art changes that perception, of what is not myself of myself, and what is myself to what is not myself. Very similar to how I interpret RNNs.