Quantum neural networks (QNN) refers to the class of neural network models, artificial or biological, which rely on principles inspired in some way from quantum mechanics.
Two different classes may be generally distinguished:
- The class of quantum neural networks which explicitly use concepts from quantum computing, such as superposition, interference, entanglement or qubits and qubit registers. Several authors have published papers on this type of QNN, however most have remained at the purely theoretical level, especially since most proposals require a functional quantum computer to be implemented. Some proposed models are networks where the neuron is modeled like a qubit, and quantum associative memory (a quantum equivalent of a Hopfield network).
- Models of biological neural networks (e.g. animal and human brains) which use concepts from quantum computing and quantum mechanics to explain the exceptional performance of biological brains as opposed to conventional computing devices, or to explain why humans (and eventually other animals) exhibit consciousness, while current computers do not. See ideas about the quantum mind.
Famous quotes containing the words quantum and/or network:
“The receipt to make a speaker, and an applauded one too, is short and easy.—Take of common sense quantum sufficit, add a little application to the rules and orders of the House, throw obvious thoughts in a new light, and make up the whole with a large quantity of purity, correctness, and elegancy of style.”
—Philip Dormer Stanhope, 4th Earl Chesterfield (1694–1773)
“Of what use, however, is a general certainty that an insect will not walk with his head hindmost, when what you need to know is the play of inward stimulus that sends him hither and thither in a network of possible paths?”
—George Eliot [Mary Ann (or Marian)