The Gated Attractors Learning Instruction Sequences (GALIS) framework, used to solve a card-matching task, as well as the n-back task, appears to be trying to unite high-level symbolic reasoning to neural networks. This is also the goal of the NEF/SPA.

What are the differences in approach and what trade-offs exist?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.