Multimodal computer image recognition based on depth neural network

Wang, Shan; Wang, YueXing; Shan, Huiling; Shi, Chunxiang

doi:10.1007/s10586-018-2422-6

Cited by 3 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The speed of improved CPSO-RELM is 2.61 times faster than CPSO-RELM. The above data indicate that for both ELM and RELM, this method can effectively promote the speed and reach high accuracy, which will make it more feasible to be used in some fields that require timeliness such as images recognition [13], Speech recognition and Unmanned aerial vehicle driving technology.…”

Section: Discussionmentioning

confidence: 92%

See 1 more Smart Citation

Improve Efficiency of Extreme Learning Machine based on Chaos Particle Swarm Optimization Method

Wen¹,

Chen²

2019

int. jour. eng. com. sci

View full text Add to dashboard Cite

Extreme Learning Machine (ELM) and Regularized Extreme Learning Machine (RELM) have advantages of fast training speed and good generalization. However, ELM/RELM often needs numerous number of hidden layer nodes to get better performance. The superabundant nodes in hidden layer maybe lead to low running speed. Thus it is not feasible to use ELM in some fields that require high speed algorithms. Therefore, in this paper, we propose an Improved ELM/RELM Optimized based on Chaos Particle Swarm Optimization (CPSO-ELM/RELM) to reduce the number of hidden layer nodes, but still maintain a desirable accuracy. At the same time, it lowers the running speed compared with other algorithms. To verify the application of this method, we design numerous experiments for ELM and RRELM. Their simulation shows that the approach improves the speed of the algorithms, and the accuracy is still high. This makes it possible to use improved CPSO-ELM/RELM in some system with high real-time requirements.

show abstract

Section: Discussionmentioning

confidence: 92%

“…Since the method of regularization was proposed, it has become the one of the most popular method in the field of machine learning [9]. ELM is based on Empirical Risk Minimization (ERM) principle and so it tends to overfit.…”

Section: Relm and Its Specific Algorithm Formulasmentioning

confidence: 99%