Analytic solution of attractor neural networks on scale-free graphs
نویسنده
چکیده
We study the influence of network topology on retrieval properties of recurrent neural networks, using replica techniques for diluted systems. The theory is presented for a network with an arbitrary degree distribution p(k) and applied to power law distributions p(k) ∼ k , i.e. to neural networks on scale-free graphs. A bifurcation analysis identifies phase boundaries between the paramagnetic phase and either a retrieval phase or a spin glass phase. Using a population dynamics algorithm, the retrieval overlap and spin glass order parameters may be calculated throughout the phase diagram. It is shown that there is an enhancement of the retrieval properties compared with a Poissonian random graph. We compare our findings with simulations. PACS numbers: 75.10.Nr, 05.20.-y, 64.60.Cn E-mail: [email protected], [email protected], [email protected], [email protected], [email protected], [email protected]
منابع مشابه
Solution of Laminar Boundary Layer and Turbulent Free Jet With Neural Networks
A novel neuro-based method is introduced to solve the laminar boundary layer and the turbulent free jet equations. The proposed method is based on cellular neural networks, CNNs, which are recently applied widely to solve partial differential equations. The effectiveness of the method is illustrated through some examples.
متن کاملSolution of Laminar Boundary Layer and Turbulent Free Jet With Neural Networks
A novel neuro-based method is introduced to solve the laminar boundary layer and the turbulent free jet equations. The proposed method is based on cellular neural networks, CNNs, which are recently applied widely to solve partial differential equations. The effectiveness of the method is illustrated through some examples.
متن کاملبهبود بازشناسی مقاوم الگو در شبکه های عصبی بازگشتی جاذب از طریق به کارگیری دینامیک های آشوب گونه
In this paper, two kinds of chaotic neural networks are proposed to evaluate the efficiency of chaotic dynamics in robust pattern recognition. The First model is designed based on natural selection theory. In this model, attractor recurrent neural network, intelligently, guides the evaluation of chaotic nodes in order to obtain the best solution. In the second model, a different structure of ch...
متن کاملResponse of degree-correlated scale-free networks to stimuli.
The response of degree-correlated scale-free attractor networks to stimuli is studied. We show that degree-correlated scale-free networks are robust to random stimuli as well as the uncorrelated scale-free networks, while assortative (disassortative) scale-free networks are more (less) sensitive to directed stimuli than uncorrelated networks. We find that the degree correlation of scale-free ne...
متن کاملEstimation of coal swelling index based on chemical properties of coal using artificial neural networks
Free swelling index (FSI) is an important parameter for cokeability and combustion of coals. In this research, the effects of chemical properties of coals on the coal free swelling index were studied by artificial neural network methods. The artificial neural networks (ANNs) method was used for 200 datasets to estimate the free swelling index value. In this investigation, ten input parameters ...
متن کامل