Sparsely Encoded Hopfield Model with Unit Replacement
نویسندگان
چکیده
منابع مشابه
Nonlinear factorization in sparsely encoded Hopfield-like neural networks
The problem of binary factorization of complex patterns in recurrent Hopfieldlike neural network was studied both theoretically and by means of computer simulation. The number and sparseness of factors mixed in patterns crucially determines the ability of an autoassociator to perform a factorization. Basing on experimental data on memory and learning one may suggest, that there exists a neural ...
متن کاملTagging Rare Events with Sparsely Encoded Data
I give a review of recent results obtained on the associative properties of a simple perceptron in the sparse coding limit : simple Hebbian rules allow to reach optimal or near optimal performances, and these performances may be obtained in the regime where the network makes errors.
متن کاملSparsely encoded local descriptor for face verification
A novel Sparsely Encoded Local Descriptor (SELD) is proposed for face verification. Different from traditional hard or soft quantization methods, we exploit linear regression (LR) model with sparsity and non-negativity constraints to extract more discriminative features (i.e. sparse codes) from local image patches sampled pixel-wisely. Sum-pooling is then imposed to integrate all the sparse cod...
متن کاملNew Computer Algorithm Enabling Simulation of Recall Process in Sparsely Encoded Hopfield-like Neural Network of Extremely Large Size
The algorithm which minimizes the required computer memory to simulate neuro-dynamics in sparsely encoded Hoppeld-like autoassociative memory is proposed. It does not require to keep in memory both connection matrix and a set of stored prototypes. The algorithm allows to simulate the recall process in the neural network of extremely large size and thus to calculate its asymptotic informational ...
متن کاملTransient Dynamics of Sparsely Connected Hopfield Neural Networks with Arbitrary Degree Distributions
Using probabilistic approach, the transient dynamics of sparsely connected Hopfield neural networks is studied for arbitrary degree distributions. A recursive scheme is developed to determine the time evolution of overlap parameters. As illustrative examples, the explicit calculations of dynamics for networks with binomial, powerlaw, and uniform degree distribution are performed. The results ar...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEICE Transactions on Information and Systems
سال: 2012
ISSN: 0916-8532,1745-1361
DOI: 10.1587/transinf.e95.d.2124