Research on the Framework of Morphological Associative Memories

Feng, Naiqin; Liu, Chunhong; Zhang, Cong-Pin; Xu, Jiucheng; Wang, Shuangxi

doi:10.3724/sp.j.1016.2010.00157

Cited by 10 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Resistance to expansion noise are presented in [28] the fifth and sixth methods are presented in [29,30]. In addition, the other six methods are proposed by Feng et al [31,32,34]. The following experiment demonstrates to some extent the anti-noise performance of these individual networks.…”

Section: Individual Network In Ufmammentioning

confidence: 86%

“…It has been well developed both in theory and application. There are many MNNs, for example, RMAM (real morphological associative memory), MBAM (morphological bidirectional associative memory), CMAM (complex MAM), FMAM (fuzzy MAM) [29], EFMAM (enhanced FMAM) [30], UFMAM (unified framework of MAM) [31], LEMAM (logarithmic exponential MAM) [32], FDSMAM (four dimensional storage MAM) [33], NR 2 FMAM (no rounding reverse FMAM) [34], etc.. The MAM theory system with good structure has formed.…”

Section: Morphological Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Study on Neural Network Integration Method Based on Morphological Associative Memory Framework

Feng

Geng

Sun

2021

Neural Process Lett

View full text Add to dashboard Cite

In traditional neural network integration, people adopt Boosting, Bagging and other methods to integrate traditional neural networks. The integration is complex, time-consuming and laborious, difficult to popularize and apply. This paper is not a continuation of this method, but another integration which is called by us morphological neural network integration (MNNI) or morphological associative memory integration (MAMI). These networks used in MAMI are a network family, with 10 family members, unified in the morphological associative memory framework. Various morphological associative memory networks can be directly used as individual networks to learn and work separately, and then synthesize to draw conclusions. The results of some experiments show that this method is not only feasible in theory, but also effective in practice. It can avoid the complexity of traditional integration method, make the integration structure simple and clear, easy to operate, save time, and therefore is a method of neural network integration with research and application value. The contribution of this paper lies in that: (1) it proposed the concept and method of MNNI and, (2) verified the effectiveness of MNNI through experiments and, (3) it has the characteristics of simplicity, saving time and labor and cost, with a good application prospect and, (4) thus promoting the development of morphological neural networks in theory and practice.

show abstract

Section: Individual Network In Ufmammentioning

confidence: 86%

Section: Morphological Neural Networkmentioning

confidence: 99%

Study on Neural Network Integration Method Based on Morphological Associative Memory Framework

Feng

Geng

Sun

2021

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…For a variety of reasons, the data barriers stand in the primary stage of large data, and the data cannot really make the maximum use of the data. 17 Data scheduling platform will make use of data rules and open data interfaces among data. The personal data, enterprise data, and government data stored in various network systems are unified into the big data platform.…”

Section: Design Of Overall Framework Model Of Relational Data Mining ...mentioning

confidence: 99%

Research on the inheritance and protection of data mining technology in national sports

Xiao

Zheng

2020

Concurrency and Computation

View full text Add to dashboard Cite

Summary In order to improve the ability of inheritance and protection of national sports, the association data mining model of inheritance and protection of national sports is proposed based on feature extraction of association rules. In this article, a new neural fuzzy normal form system is designed, which can perform both feature analysis and SI(sine) integration. The time series analysis model of the inheritance and protection correlation data in the national sports are constructed, the overall frame model of the inheritance and protection correlation data mining in the national sports is designed. The ability of adaptive data fusion and feature registration is improved. The simulation results show that the proposed method has good accuracy and strong ability of feature matching in the correlation data mining of inheritance and protection in national sports, and it can improve the function of inheritance and protection of national sports.

show abstract

“…Wang et al treated input vectors and output vectors as fuzzy sets, therefore they presented the fuzzy morphological associative memories (FMAM) [24], enhanced FMAM (EFMAM) based on empirical kernel map [22] and economized EFMAM (E 2 FMAM) [23]. Feng et al proposed the unified framework of morphological associative memories in complex domain (UFMAM CD ) [3], and the MAM based on four-dimensional storage (MAM-FDS) [7], and the Logarithmic and exponential MAM (LEMAM) [6].…”

Section: Introductionmentioning

confidence: 99%

“…Wang et al also pointed out that morphological auto-associative memories (auto-MAM) and fuzzy morphological auto-associative memories (auto-FMAM) have many attractive advantages such as unlimited storage capacity, one-shot recall speed and good noise-tolerance to single erosive or dilative noise. Morphological associative memories have many applications in pattern recognition [19,21], image processing [2,5], classification and prediction [20], psychology research [4], and so on.…”

Section: Introductionmentioning

confidence: 99%

No Rounding Reverse Fuzzy Morphological Associative Memories

Feng¹,

Yao²

2016

NNW

View full text Add to dashboard Cite

Precise wind energy potential assessment is vital for wind energy generation and planning and development of new wind power plants. This work proposes and evaluates a novel two-stage method for location-specific wind energy potential assessment. It combines accurate statistical modelling of annual wind direction distribution in a given location with supervised machine learning of efficient estimators that can approximate energy efficiency coefficients from the parameters of optimized statistical wind direction models. The statistical models are optimized using differential evolution and energy efficiency is approximated by evolutionary fuzzy rules.

show abstract

Research on the Framework of Morphological Associative Memories

Cited by 10 publications

References 9 publications

Study on Neural Network Integration Method Based on Morphological Associative Memory Framework

Study on Neural Network Integration Method Based on Morphological Associative Memory Framework

Research on the inheritance and protection of data mining technology in national sports

No Rounding Reverse Fuzzy Morphological Associative Memories

Contact Info

Product

Resources

About