. . . . "0303-2647" . "[7034E28171C9]" . "7"^^ . "1-3" . "Hebb rule; Hopfield network; auto-associative neural network"@en . "440829" . "We investigate an artificial neural network model with a modified Hebb rule. It is an auto-associative neural network similar to the Hopfield model and to the Willshaw model. It has properties of both of these models. Another property is that the patterns are sparsely coded and are stored in cycles of synchronous neural activities. The cycles of activity for some ranges of parameter increase the capacity of the model. We discuss basic properties of the model and some of the implementation issues, namely optimizing of the algorithms. We describe the modification of the Hebb learning rule, the learning algorithm, the generation of patterns, decomposition of patterns into cycles and pattern recall." . . "Pattern Storage in a Sparsely Coded Neural Network with Cyclic Activation" . "Z(MSM6840770012)" . . "GB - Spojen\u00E9 kr\u00E1lovstv\u00ED Velk\u00E9 Brit\u00E1nie a Severn\u00EDho Irska" . "257;263" . . "89" . "1"^^ . . "Z\u00E1znam pam\u011B\u0165ov\u00FDch stop v neuronov\u00E9 s\u00EDti pomoc\u00ED \u0159\u00EDdk\u00E9ho k\u00F3dov\u00E1n\u00ED a cyklick\u00E9 aktivace"@cs . "Pr\u00E1ce studuje origin\u00E1ln\u00ED design neuronov\u00E9 s\u00EDt\u011B. Ta je inspirovan\u00E1 Hopfieldovou a Willshawovou s\u00EDt\u00ED s pou\u017Eit\u00EDm Hebbova pravidla modifikovan\u00E9ho tak, aby cyklicky aktivovalo skupiny neuron\u016F. Pr\u00E1ce prezentuje implementaci a odhady kapacity t\u00E9to s\u00EDt\u011B."@cs . . "RIV/68407700:21460/07:12132181" . "Mar\u0161\u00E1lek, Petr" . "3"^^ . "Pattern Storage in a Sparsely Coded Neural Network with Cyclic Activation"@en . "Biosystems" . . . . "Pattern Storage in a Sparsely Coded Neural Network with Cyclic Activation"@en . "21460" . . . "Kuriscak, E." . "Stroffek, J." . "Pattern Storage in a Sparsely Coded Neural Network with Cyclic Activation" . "RIV/68407700:21460/07:12132181!RIV08-MSM-21460___" . . "Z\u00E1znam pam\u011B\u0165ov\u00FDch stop v neuronov\u00E9 s\u00EDti pomoc\u00ED \u0159\u00EDdk\u00E9ho k\u00F3dov\u00E1n\u00ED a cyklick\u00E9 aktivace"@cs . "We investigate an artificial neural network model with a modified Hebb rule. It is an auto-associative neural network similar to the Hopfield model and to the Willshaw model. It has properties of both of these models. Another property is that the patterns are sparsely coded and are stored in cycles of synchronous neural activities. The cycles of activity for some ranges of parameter increase the capacity of the model. We discuss basic properties of the model and some of the implementation issues, namely optimizing of the algorithms. We describe the modification of the Hebb learning rule, the learning algorithm, the generation of patterns, decomposition of patterns into cycles and pattern recall."@en .