-
Announcement - Accepted talk at ICAM 2020
The paper “Designing arithmetic neural primitive for sub-symbolic aggregation of linguistic assessments” was accepted to a conference The XIII International Conference COMPUTER-AIDED TECHNOLOGIES IN APPLIED MATHEMATICS (ICAM 2020) 07-09 September 2020.
-
TPRs in Linguistic Decision Making
The overall idea is to combine separate neural networks which perform critical sub-tasks of manipulation without training (called primitives) within a single meta-network capable of producing a final solution of the multi-criteria choice problem. Possible scheme of such combination is below. NOTE: this topic will be covered at coming conferences...
-
Oral talk at ICECCE 2020
The paper “Automatic construction of tensor product variable binding neural networks for neural-symbolic intelligent systems” was presented at a conference The 2nd International Conference on Electrical, Communication and Computer Engineering (ICECCE 2020) 12-13 June 2020. The talk can be found online:
-
Tensor Product Representations (TPRs) Literature
Tensor Product Variable Binding is a way to transform the symbolic structure into the vector format [1] using the tensor product operation. Definition 1. Filler – a particular instance of the given structural type. Definition 2. Role – a function that filler presents in a structure. There are several recent...
