Creating ensembles of random but "realistic" topologies for complex systems is crucial for many tasks such as benchmark generation and algorithm analysis. In general, exp...
The parallel genetic algorithm (PGA) is a prototype of a new kind of a distributed algorithm. It is based on a parallel search by individuals all of which have the complete proble...
We propose linear time solutions to two much celebrated NP-complete problems, namely the 3CNF-SAT and the directed Hamiltonian Path Problem (HPP), based on AHNEPs having all resour...
Models of associative memory usually have full connectivity or if diluted, random symmetric connectivity. In contrast, biological neural systems have predominantly local, non-symm...
Causal learning methods are often evaluated in terms of their ability to discover a true underlying directed acyclic graph (DAG) structure. However, in general the true structure ...
David Duvenaud, Daniel Eaton, Kevin P. Murphy, Mar...