{
"$type": "site.standard.document",
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreiclixbmeatzr3bfydsex6rw2jylexba6gulpdgv6zxnyypwkh76pa"
},
"mimeType": "image/png",
"size": 97852
},
"description": "A probabilistic neural network, comprising a hidden layer of neurons, each computing respective membership matrix elements for an input vector of the neural network according to a respective radial basis function defined by a respective spread factor and according to the distance of the input…",
"path": "/patents/1016498",
"publishedAt": "2011-01-19T00:00:00.000Z",
"site": "at://did:plc:oql6ds5vnff4ugar6rruliwd/site.standard.publication/3mn3ohu7oxx5w",
"tags": [
"F02D35/023",
"ST MICROELECTRONICS SRL [IT]"
],
"textContent": "A probabilistic neural network, comprising a hidden layer of neurons, each computing respective membership matrix elements for an input vector of the neural network according to a respective radial basis function defined by a respective spread factor and according to the distance of the input vector from a respective constant vector, wherein said hidden layer comprises at least two neurons having different spread factors (S). [0002] A method of training the novel probabilistic neural network is also disclosed.",
"title": "Probabilistic neural network and relative training method"
}