A fully differentiable recurrent visual attention model to count the number of blobs. Some code / ideas taken from this implementation (https://github.com/ericjang/draw) of this paper (http://arxiv.org/pdf/1502.04623.pdf), and built upon this implementation (https://github.com/jlindsey15/DRAM).
-
Notifications
You must be signed in to change notification settings - Fork 1
numberlearning/DRAM
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Deep recurrent attentional neural network model simulating human mathematical cognition. Demonstrating human-like development of ability to estimate and count number.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published