Skip to Main Content
A meme in the context of optimization represents a unit of algorithmic abstraction that dictates how solution search is carried out. At a higher level, a meta-meme serves as an encapsulation of the scheme of interplay between memes involved in the search process. This paper puts forth the notion of neural meta-memes to extend the collective capacity of memes in problem-solving. We term this as Neural Meta-Memes Framework (NMMF) for combinatorial optimization. NMMF models basic optimization algorithms as memes and manages them dynamically. We show the efficacy of the proposed NMMF through empirical study on a class of combinatorial optimization problem, the quadratic assignment problem (QAP).