Recently proposed neural architecture search (NAS) algorithms adopt predictors to accelerate search. The capability of accurately predict the performance metrics is critical NAS, but obtaining training datasets for often time-consuming. How obtain a predictor with high prediction accuracy using small amount data central problem predictor-based NAS. Here, new encoding scheme first devised calcul...

A challenge in hybrid evolutionary algorithms is to define efficient strategies to cover all search space, applying local search only in actually promising search areas. This paper proposes a way of detecting promising search areas based on clustering. In this approach, an iterative clustering works simultaneously to an evolutionary algorithm accounting the activity (selections or updatings) in...

Inspired by the notion of surprise for unconventional discovery we introduce a general search algorithm we name surprise search as a new method of evolutionary divergent search. Surprise search is grounded in the divergent search paradigm and is fabricated within the principles of evolutionary search. The algorithm mimics the self-surprise cognitive process and equips evolutionary search with t...

In this paper, we proposed Evolutionary Organizational Search (EOS), an optimization method for the organizational control of multi-agent systems (MASs) based on genetic programming (GP). EOS adds to the existing armory a metaheuristic extension, which is capable of efficient search and less vulnerable to stalling at local optima than greedy methods due to its stochastic nature. EOS employs a f...

The flexible architecture of evolutionary algorithms allows specialised models to be obtained with the aim of performing as other search methods do, but more satisfactorily. In fact, there exist several evolutionary proposals in the literature that play the role of local search methods. In this paper, we make a step forward presenting a specialised evolutionary approach that carries out a search

Training of neural networks by local search such as gradient-based algorithms could be diicult. This calls for the development of alternative training algorithms such as evolutionary search. However, training by evolutionary search often requires long computation time. In this chapter, we investigate the possibilities of reducing the time taken by combining the eeorts of local search and evolut...

Stochastic search algorithms can be used to perform rapid six-dimensional molecular-replacement searches. A molecular-replacement procedure has been developed that uses an evolutionary algorithm to simultaneously optimize the orientation and position of a search model in a unit cell. Here, the performance of this algorithm and its dependence on search model quality and choice of target function...

In this paper, we consider the problem of finding good next moves in two-player games. Traditional search algorithms, such as minimax and alpha-beta pruning, suffer great temporal and spatial expansion when exploring deeply into search trees to find better next moves. The evolution of genetic algorithms with the ability to find global or near global optima in limited time seems promising, but t...

In Natural evolution, a mutation may be lethal, causing an abrupt end to an evolving lineage. This fact has a tendency to cause evolution to “prefer” mutationally robust solutions (which can in turn slow innovation), an effect that has been studied previously, especially in the context of evolution on neutral plateaux. Here, we tackle related issues but from the perspective of a practical optim...

An important factor in the successful application of evolutionary techniques to real-world problems is the incorporation of domain knowledge. One form such knowledge often takes is the possession of one or more high-quality solutions. Non-random initialisation, or inoculation, of the population in an evolutionary algorithm provides a way to incorporate such knowledge. A body of folklore about t...