An envelopment learning procedure for improving prediction accuracies of grey models

2020 ◽  
Vol 139 ◽  
pp. 106185 ◽  
Author(s):  
Chien-Chih Chen ◽  
Che-Jung Chang ◽  
Zheng-Yun Zhuang ◽  
Der-Chiang Li
2021 ◽  
Vol 11 (4) ◽  
pp. 423
Author(s):  
Markus Fendt ◽  
Claudia Paulina Gonzalez-Guerrero ◽  
Evelyn Kahl

Rats can acquire fear by observing conspecifics that express fear in the presence of conditioned fear stimuli. This process is called observational fear learning and is based on the social transmission of the demonstrator rat’s emotion and the induction of an empathy-like or anxiety state in the observer. The aim of the present study was to investigate the role of trait anxiety and ultrasonic vocalization in observational fear learning. Two experiments with male Wistar rats were performed. In the first experiment, trait anxiety was assessed in a light–dark box test before the rats were submitted to the observational fear learning procedure. In the second experiment, ultrasonic vocalization was recorded throughout the whole observational fear learning procedure, and 22 kHz and 50 kHz calls were analyzed. The results of our study show that trait anxiety differently affects direct fear learning and observational fear learning. Direct fear learning was more pronounced with higher trait anxiety, while observational fear learning was the best with a medium-level of trait anxiety. There were no indications in the present study that ultrasonic vocalization, especially emission of 22 kHz calls, but also 50 kHz calls, are critical for observational fear learning.


Author(s):  
Joseph H. Cihon ◽  
Mary Jane Weiss ◽  
Julia L. Ferguson ◽  
Justin B. Leaf ◽  
Thomas Zane ◽  
...  

Research addressing food selectivity has involved intrusive techniques such as escape extinction. It is possible that observational learning methods employed in previous studies could provide the desired results with respect to food selectivity without the need for invasive physical interventions. The purpose of this study was to evaluate the effectiveness of an observational learning procedure on the selection of food items of three children diagnosed with autism spectrum disorder. Baseline consisted of a simple task after which a choice was presented between high- and low-preferred foods. The intervention consisted of observing an adult engage in the same task and selecting the low-preferred food while making favorable comments and engaging with the food in novel ways. The results of a reversal design demonstrated that selection of the low-preferred food only occurred following the introduction of the intervention, and all three participants engaged in flexible responding as a result of the intervention.


1999 ◽  
Vol 11 (2) ◽  
pp. 483-497 ◽  
Author(s):  
Ran Avnimelech ◽  
Nathan Intrator

We present a new supervised learning procedure for ensemble machines, in which outputs of predictors, trained on different distributions, are combined by a dynamic classifier combination model. This procedure may be viewed as either a version of mixture of experts (Jacobs, Jordan, Nowlan, & Hinton, 1991), applied to classification, or a variant of the boosting algorithm (Schapire, 1990). As a variant of the mixture of experts, it can be made appropriate for general classification and regression problems by initializing the partition of the data set to different experts in a boostlike manner. If viewed as a variant of the boosting algorithm, its main gain is the use of a dynamic combination model for the outputs of the networks. Results are demonstrated on a synthetic example and a digit recognition task from the NIST database and compared with classical ensemble approaches.


Kybernetes ◽  
2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Yitong Liu ◽  
Yang Yang ◽  
Dingyu Xue ◽  
Feng Pan

PurposeElectricity consumption prediction has been an important topic for its significant impact on electric policies. Due to various uncertain factors, the growth trends of electricity consumption in different cases are variable. However, the traditional grey model is based on a fixed structure which sometimes cannot match the trend of raw data. Consequently, the predictive accuracy is variable as cases change. To improve the model's adaptability and forecasting ability, a novel fractional discrete grey model with variable structure is proposed in this paper.Design/methodology/approachThe novel model can be regarded as a homogenous or non-homogenous exponent predicting model by changing the structure. And it selects the appropriate structure depending on the characteristics of raw data. The introduction of fractional accumulation enhances the predicting ability of the novel model. And the relative fractional order r is calculated by the numerical iterative algorithm which is simple but effective.FindingsTwo cases of power load and electricity consumption in Jiangsu and Fujian are applied to assess the predicting accuracy of the novel grey model. Four widely-used grey models, three classical statistical models and the multi-layer artificial neural network model are taken into comparison. The results demonstrate that the novel grey model performs well in all cases, and is superior to the comparative eight models.Originality/valueA fractional-order discrete grey model with an adaptable structure is proposed to solve the conflict between traditional grey models' fixed structures and variable development trends of raw data. In applications, the novel model has satisfied adaptability and predicting accuracy.


2018 ◽  
Vol 2018 ◽  
pp. 1-10
Author(s):  
Lifeng Wu ◽  
Yan Chen

To deal with the forecasting with small samples in the supply chain, three grey models with fractional order accumulation are presented. Human judgment of future trends is incorporated into the order number of accumulation. The output of the proposed model will provide decision-makers in the supply chain with more forecasting information for short time periods. The results of practical real examples demonstrate that the model provides remarkable prediction performances compared with the traditional forecasting model.


Author(s):  
David LIGHTFOOT

This paper reviews the problems of the deterministic and predictive view of language change initiated by nineteenth century linguists and shows that such a view is still present in many analyses proposed by twentieth century linguists. As an alternative to such a view, the paper discusses an approach along the lines of Niyogi and Berwick (1997), which takes the explanation for long-term tendencies to be a function of the architecture of UG and the learning procedure and of the way in which populations of speakers behave.


Sign in / Sign up

Export Citation Format

Share Document