Abstract | ||
---|---|---|
A new neural network architecture is presented which encompasses functions similar to those in a biological brain, such as lateral and feedback connections and neurons. The neurons are randomly distributed on the 2D-planes. Each neuron on each plane can connect to a neighborhood of neurons at the next layer (plane), as well as receive feedback from neurons on that layer, or any other layer in the immediate or distant vicinity. In addition, lateral inhibitory connectivity within a layer adds to the flexibility and generalization abilities of the neural network |
Year | DOI | Venue |
---|---|---|
1997 | 10.1109/ICNN.1997.614673 | Neural Networks,1997., International Conference |
Keywords | Field | DocType |
circuit feedback,feedforward neural nets,generalisation (artificial intelligence),neural net architecture,3d neural architecture,feedback,feedforward neural network,flexibility,generalization,lateral inhibitory connectivity,neuron connection,pattern analysis,biomedical engineering,three dimensional,radio frequency,pattern recognition,neural network,neurofeedback | Topology,Architecture,Feedforward neural network,Computer science,Inhibitory postsynaptic potential,Artificial intelligence,Echo state network,Artificial neural network,Winner-take-all,Spiking neural network,Neuron | Conference |
Volume | ISBN | Citations |
4 | 0-7803-4122-8 | 0 |
PageRank | References | Authors |
0.34 | 1 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Evangelia Micheli-Tzanakou | 1 | 14 | 4.50 |
Dasey, T.J. | 2 | 5 | 1.61 |