seGEN: Sample-Ensemble Genetic Evolutional Network Model
نویسندگان
چکیده
Deep learning, a rebranding of deep neural network research works, has achieved remarkable success in recent years. With multiple hidden layers, deep learning models aim at computing hierarchical features or representations of the observational data. Meanwhile, due to its severe disadvantages in data consumption, computational resources, parameter tuning eorts and the lack of result explainability, deep learning has also suered from lots of criticism. In this paper, we will introduce a new representation learning model, namely “Sample-Ensemble Genetic Evolutional Network” (seGEN), which can serve as an alternative approach to deep learning models. Instead of building one single deep model, based on a set of sampled sub-instances, seGEN adopts a genetic-evolutional learning strategy to build a group of unit models generations by generations. e unit models incorporated in seGEN can be either traditional machine learning models or the recent deep learning models with a much “smaller” and “shallower” architecture. e learning results of each instance at the nal generation will be eectively combined from each unit model via diusive propagation and ensemble learning strategies. From the computational perspective, seGEN requires far less data, fewer computational resources and parameter tuning works, but has sound theoretic interpretability of the learning process and results. Extensive experiments have been done on real-world network structured datasets, and the experimental results obtained by seGEN have demonstrate its advantages over the other state-of-the-art representation learning models.
منابع مشابه
Ensemble strategies to build neural network to facilitate decision making
There are three major strategies to form neural network ensembles. The simplest one is the Cross Validation strategy in which all members are trained with the same training data. Bagging and boosting strategies pro-duce perturbed sample from training data. This paper provides an ideal model based on two important factors: activation function and number of neurons in the hidden layer and based u...
متن کاملEnsemble of M5 Model Tree Based Modelling of Sodium Adsorption Ratio
This work reports the results of four ensemble approaches with the M5 model tree as the base regression model to anticipate Sodium Adsorption Ratio (SAR). Ensemble methods that combine the output of multiple regression models have been found to be more accurate than any of the individual models making up the ensemble. In this study additive boosting, bagging, rotation forest and random subspace...
متن کاملGenetic diversity within the Iranian spiny-tailed lizards and predicting species distribution in climate change conditions
There are different methods to investigate the effects of climatic fluctuations on the biota, two of which, molecular phylogeography and SDM, are the most useful tools to trace the past climate induced modifications on species’ geographic distributions. In this study, seven samples were collected from the species distribution range in Iran for the purpose of measuring the genetic variation with...
متن کاملImproving Accuracy in Intrusion Detection Systems Using Classifier Ensemble and Clustering
Recently by developing the technology, the number of network-based servicesis increasing, and sensitive information of users is shared through the Internet.Accordingly, large-scale malicious attacks on computer networks could causesevere disruption to network services so cybersecurity turns to a major concern fornetworks. An intrusion detection system (IDS) could be cons...
متن کاملFault Detection of Bearings Using a Rule-based Classifier Ensemble and Genetic Algorithm
This paper proposes a reduct construction method based on discernibility matrix simplification. The method works with genetic algorithm. To identify potential problems and prevent complete failure of bearings, a new method based on rule-based classifier ensemble is presented. Genetic algorithm is used for feature reduction. The generated rules of the reducts are used to build the candidate base...
متن کامل