The Newspaper Designer’s Handbook

Rotterdam cube houses.

“The walls and windows are angled at 54.7 degrees. The total area of the apartment is around 100 square meters, but around a quarter of the space is unusable because of the walls that are under the angled ceilings.”

A note to self about form over function in the real world.

new-aesthetic:

More “highlights” from Google’s Neural Network research (full album via jonty).

new-aesthetic:

Google Research Blog: Inceptionism: Going Deeper into Neural Networks

One of the challenges of neural networks is understanding what exactly goes on at each layer. We know that after training, each layer progressively extracts higher and higher-level features of the image, until the final layer essentially makes a decision on what the image shows. For example, the first layer maybe looks for edges or corners. Intermediate layers interpret the basic features to look for overall shapes or components, like a door or a leaf. The final few layers assemble those into complete interpretations—these neurons activate in response to very complex things such as entire buildings or trees.

One way to visualize what goes on is to turn the network upside down and ask it to enhance an input image in such a way as to elicit a particular interpretation. Say you want to know what sort of image would result in “Banana.” Start with an image full of random noise, then gradually tweak the image towards what the neural net considers a banana (see related work in [1], [2], [3], [4]). By itself, that doesn’t work very well, but it does if we impose a prior constraint that the image should have similar statistics to natural images, such as neighboring pixels needing to be correlated.

The trick is to pick the right sorts of projects for the top of the list. The ideal sorts of things have two characteristics, First, they seem to have clear deadlines (but really don’t). Second, they seem awfully important (but really aren’t). Luckily, life abounds with such tasks.