Learning and analyzing vector encoding of symbolic representations

03/10/2018
by   Roland Fernandez, et al.
0

We present a formal language with expressions denoting general symbol structures and queries which access information in those structures. A sequence-to-sequence network processing this language learns to encode symbol structures and query them. The learned representation (approximately) shares a simple linearity property with theoretical techniques for performing this task.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset