Conversation

This Tweet was deleted by the Tweet author. Learn more
Replying to
I don’t think it’s solvable within the deep learning class of techniques tbh. Needs an injection of both GOFAI and data on sensory-verbal correlations beyond narrow application-tagged sets like cars or driverless car road images. Needs open-tagged broad image sets to start.
1
Replying to and
Like at some level it needs to know that “car” refers to objects which prototypically look like 🚗, and that the little circly things are “wheels” but beyond self-driving app context.
1
This Tweet was deleted by the Tweet author. Learn more
Replying to
Because verbalized data from human culture is a very reductive, low-dimensional slice of all human cognition. Trillions of training words sounds impressive until you think about i/o bit rate of just a minute of a single human life. It’s the equivalent of billions of words.
1
4
This Tweet was deleted by the Tweet author. Learn more
This Tweet was deleted by the Tweet author. Learn more
This Tweet was deleted by the Tweet author. Learn more
Replying to and
Not sure what kind of classification models the solution attempts are using, but pretty sure they're not informed by ~125 years of work on this in the humanities. Todorov as starting point if I had to offer an example