GEN Model: An Alternative Approach to Deep Neural Network Models
This offers an alternative approach to deep neural networks, potentially improving learning effectiveness, efficiency, and interpretability for machine learning practitioners, though it appears incremental as it builds on evolutionary strategies.
The authors tackled the problem of deep learning models by proposing the GEN Model, which uses a genetic-evolutionary strategy with shallow unit models instead of a single deep structure, and demonstrated outstanding performance in effectiveness and efficiency on benchmark datasets compared to state-of-the-art methods.
In this paper, we introduce an alternative approach, namely GEN (Genetic Evolution Network) Model, to the deep learning models. Instead of building one single deep model, GEN adopts a genetic-evolutionary learning strategy to build a group of unit models generations by generations. Significantly different from the wellknown representation learning models with extremely deep structures, the unit models covered in GEN are of a much shallower architecture. In the training process, from each generation, a subset of unit models will be selected based on their performance to evolve and generate the child models in the next generation. GEN has significant advantages compared with existing deep representation learning models in terms of both learning effectiveness, efficiency and interpretability of the learning process and learned results. Extensive experiments have been done on diverse benchmark datasets, and the experimental results have demonstrated the outstanding performance of GEN compared with the state-of-the-art baseline methods in both effectiveness of efficiency.