Mixed state in a sparsely encoded associative memory model storing ultrametric patterns
نویسندگان
چکیده
When mixed states are composed of s memory patterns, s types of mixed states, which can become equilibrium states of the model, can be generated. We found that the storage capacity for all mixed states diverged as 1/|f log f | when the s memory patterns were given correlation. We also investigated how the storage capacity of them change on the correlation coefficient between s memory patterns. Under the condition that the firing rate f is fixed, as the correlation coefficient increased, the storage capacity of the mixed state composed of all s memory patterns increased, while that of the mixed states composed of only some of the s memory patterns decreased.
منابع مشابه
Analysis of Oscillator Neural Networks for Sparsely Coded Phase Patterns
We study a simple extended model of oscillator neural networks capable of storing sparsely coded phase patterns, in which information is encoded both in the mean firing rate and in the timing of spikes. Applying the methods of statistical neurodynamics to our model, we theoretically investigate the model’s associative memory capability by evaluating its maximum storage capacities and deriving i...
متن کاملMixed states on neural network with structural learning
We investigated the properties of mixed states in a sparsely encoded associative memory model with a structural learning method. When mixed states are made of s memory patterns, s types of mixed states, which become equilibrium states of the model, can be generated. To investigate the properties of s types of the mixed states, we analyzed them using the statistical mechanical method. We found t...
متن کاملBi-stability of mixed states in neural network storing hierarchical patterns
We discuss the properties of equilibrium states in an autoassociative memory model storing hierarchically correlated patterns (hereafter, hierarchical patterns). We will show that symmetric mixed states (hereafter, mixed states) are bi-stable on the associative memory model storing the hierarchical patterns in a region of the ferromagnetic phase. This means that the first-order transition occur...
متن کاملCapacity and Error Correction Ability of Sparsely Encoded Associative Memory with Forgetting Process
Associative memory model of neural networks can not store items more than its memory capacity. When new items are given one after another, its connection weights should be decayed so that the number of stored items does not exceed the memory capacity (forgetting process). This paper analyzes the sparsely encoded associative memory, and presents the optimal decay rate that maximizes the number o...
متن کاملA Neural Network-based Associative Memory for Storing Complex-valued Patterns
A neural network-based associative memory for storing complex patterns is proposed. Two variations of the model are proposed: (1) discrete model and, (2) continuous model. The latter approaches the former as a limit. A crude capacity estimate for the discrete model is made. Network weights can be calculated in one step using a complex outer-product rule or can be adjusted adaptively using a Heb...
متن کامل