Refine
Departments, institutes and facilities
Document Type
- Article (1)
- Conference Object (1)
Language
- English (2)
Has Fulltext
- no (2) (remove)
Keywords
- regression (2) (remove)
The reported research examines the impact of product portfolio labeling strategies on brand reputation and equity. A netnographic approach allowed to observe winery portfolio labeling approaches and create a typology of winery labeling strategies. Expert evaluation served to assess the dependent variable brand equity by deploying a regression analysis. For the observed wine industry, being part of the food industry, creating consistent and recognizable brands has a direct relevance for reducing (sustainability-related) food information overload and thereby building sustainable brand equity. The results uncover the relative importance of each of the six identified labeling strategies as well as their impact on reputation and brand equity creation. The results point to the need to establish a consistent, strategically founded product communication. Such an approach, with a positive effect on reputation building can serve to build sustainable brand equity. “Stuck in the middle”-type strategies apparently diminish winery brand equity exploitation. The findings contribute to the knowledge on food labels in product communication strategies and their impact on organizational brand equity, thereby having high relevance for the implementation of environmental certification initiatives in an organizational context. The article deploys a novel research approach in an under-researched area to provide new insights for further research as well as implications for practice.
Neuroevolution methods evolve the weights of a neural network, and in some cases the topology, but little work has been done to analyze the effect of evolving the activation functions of individual nodes on network size, an important factor when training networks with a small number of samples. In this work we extend the neuroevolution algorithm NEAT to evolve the activation function of neurons in addition to the topology and weights of the network. The size and performance of networks produced using NEAT with uniform activation in all nodes, or homogenous networks, is compared to networks which contain a mixture of activation functions, or heterogenous networks. For a number of regression and classification benchmarks it is shown that, (1) qualitatively different activation functions lead to different results in homogeneous networks, (2) the heterogeneous version of NEAT is able to select well performing activation functions, (3) the produced heterogeneous networks are significantly smaller than homogeneous networks.