Abstract
As a human brain-like computational model that can reflect the cognitive function of the brain, the problem of dynamic analysis of associative memory neural networks has attracted the attention of scholars. This paper combines associative memory neural networks with enterprise financial management risks, studies the synchronization control and stability analysis problems of unidirectional associative memory-like human brain amnestic neural networks with perturbation and mixed time-varying time lags, proposes a bidirectional associative memory-like brain stochastic amnestic neural network model with mixed time-varying time lags, designs a discrete-time sampling control strategy based on the model, and studies various types of recent financial risks. Based on the early warning research, based on the associative memory neural network method, we propose to reconstruct the risk categories, including improving the enterprise risk management system, enhancing the awareness of financial risk management from top to bottom, and strengthening the core competitiveness of the enterprise itself and control measures for financing, investment, operation, and cash flow risks.
Highlights
Associative memory neural network is by imitating the working pattern of neuronal cells in the human brain; firstly, the pattern to be memorized is stored in the form of weight network of the neural network; when receiving the information of incomplete or defective pattern from outside, the neural network at this time makes the input pattern continuously change its value and converge to the memorized pattern by massive parallel computation. e neural network has a good robust performance, which means that the associative memory neural network has a good fault tolerance performance. e patterns to be memorized are first stored in the form of a network of weights of the neural network
Self-associative memory refers to the application of associative memory in which the initial pattern of input is identical to the remembered pattern of output. e first step in self-associative memory is to deposit the desired memorized pattern in a specific form into the network weights through the learning algorithm of a neural network [1]. en, it is possible to input the pattern with cue information, and the neural network performs continuous iterative operations to give the correct output, and this cue information is not the complete word but has noisy information, but the neural network is still able to calculate to get the remembered word information; i.e., this associative memory neural network has a certain degree of fault tolerance
Computational Intelligence and Neuroscience values of each neuron when the neural network is in a stable state; that is, generally, a stable point of the neural network can store a pattern, and the determination of the value of the stable point needs to be set according to the necessary conditions required by the associative memory neural network model adopted in this chapter, generally by substituting the memory pattern into the set of differential equations of the neural network, listing the corresponding inequality based on the above necessary conditions, and relating this inequality to the system of differential equations coupled to solve a specific set of solutions and eventually determine a more suitable weight [2]. is process is performed using specific training algorithms
Summary
Associative memory neural network is by imitating the working pattern of neuronal cells in the human brain; firstly, the pattern to be memorized is stored in the form of weight network of the neural network; when receiving the information of incomplete or defective pattern from outside, the neural network at this time makes the input pattern continuously change its value and converge to the memorized pattern by massive parallel computation. e neural network has a good robust performance, which means that the associative memory neural network has a good fault tolerance performance. e patterns to be memorized are first stored in the form of a network of weights of the neural network. E first step in self-associative memory is to deposit the desired memorized pattern (e.g., the word computer) in a specific form into the network weights through the learning algorithm of a neural network [1]. Computational Intelligence and Neuroscience values of each neuron when the neural network is in a stable state; that is, generally, a stable point of the neural network can store a pattern, and the determination of the value of the stable point needs to be set according to the necessary conditions required by the associative memory neural network model adopted in this chapter, generally by substituting the memory pattern into the set of differential equations of the neural network, listing the corresponding inequality based on the above necessary conditions, and relating this inequality to the system of differential equations coupled to solve a specific set of solutions and eventually determine a more suitable weight [2]. Based on associative memory neural network, this paper combines the relevant theoretical literature on enterprise financial risk control with the specific case of financial risk control of the Storm Group and researches the identification, analysis, and evaluation of financial risk and control of enterprises, hoping to play a supplementary verification role to the current theoretical research on financial risk control in enterprises
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
