No Regular Behavior Pattern in Neural Network Execution – A Matlab Experience

Under the impact of COVID-19, research on behavior recognition are highly needed. In this paper, we combine the algorithm of self-adaptive coder and recurrent neural network to realize the research of behavior pattern recognition. At present, most of the research of human behavior recognition is focused on the video data, which is based on the video number. At the same time, due to the complexity of video image data, it is easy to violate personal privacy. With the rapid development of Internet of things technology, it has attracted the attention of a large number of experts and scholars. Researchers have tried to use many machine learning methods, such as random forest, support vector machine and other shallow learning methods, which perform well in the laboratory environment, but there is still a long way to go from practical application. In this paper, a recursive neural network algorithm based on long and short term memory (LSTM) is proposed to realize the recognition of behavior patterns, so as to improve the accuracy of human activity behavior recognition.

Download Full-text

Neural Network Model and Design Patterns on Fuzzy Evaluation System of Special Electromechanical Equipment

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.510.239 ◽

2012 ◽

Vol 510 ◽

pp. 239-243

Author(s):

Jian Ping Ye ◽

Lin Xiang Shi

Keyword(s):

Neural Network ◽

Network Model ◽

Neural Network Model ◽

Design Patterns ◽

Evaluation System ◽

Behavior Pattern ◽

Fuzzy Evaluation ◽

Mvc Pattern ◽

Main Class ◽

Electromechanical Equipment

According to the physical characteristics and safety requirements, the evaluation levels of special electromechanical equipment were created. The five-layer neural network model was created according to the multi-layer neural network model. The first layer is input layer, the last layer is output layer, and the others are hidden layers. The software structure of evaluation system was designed, and the main class diagram was designed with UML. The relations among views, data model and dispatch controller were designed with MVC pattern. The factory method was used to instantiate view objects according to the object creation pattern. The ITERATOR pattern of structural pattern was used to find out view objects in the view object aggregation. The strategy pattern of behavior pattern was used to encapsulate different neural network algorithms.

Download Full-text

Positive Neural Networks in Discrete Time Implement Monotone-Regular Behaviors

Neural Computation ◽

10.1162/neco_a_00789 ◽

2015 ◽

Vol 27 (12) ◽

pp. 2623-2660 ◽

Cited By ~ 4

Author(s):

Tom J. Ameloot ◽

Jan Van den Bussche

Keyword(s):

Neural Network ◽

Neural Networks ◽

Discrete Time ◽

Expressive Power ◽

Regular Languages ◽

Regular Behavior ◽

Multiple Input

We study the expressive power of positive neural networks. The model uses positive connection weights and multiple input neurons. Different behaviors can be expressed by varying the connection weights. We show that in discrete time and in the absence of noise, the class of positive neural networks captures the so-called monotone-regular behaviors, which are based on regular languages. A finer picture emerges if one takes into account the delay by which a monotone-regular behavior is implemented. Each monotone-regular behavior can be implemented by a positive neural network with a delay of one time unit. Some monotone-regular behaviors can be implemented with zero delay. And, interestingly, some simple monotone-regular behaviors cannot be implemented with zero delay.

Download Full-text