2018
Improving the Universality and Learnability of Neural Programmer-Interpreters with Combinator Abstraction
ICLR 2018poster
To overcome the limitations of Neural Programmer-Interpreters (NPI) in its universality and learnability, we propose the incorporation of combinator abstraction into neural programing and a new NPI architecture to support this abstraction, which we call Combinatory Neural Programmer-Interpreter (CNP…