33,99 €
inkl. MwSt.
Versandkostenfrei*
Versandfertig in 6-10 Tagen
payback
17 °P sammeln
  • Broschiertes Buch

Artificial intelligence is becoming increasingly present in our society. To this end, several strategies have been created. Artificial Neural Networks was one of them and has several architectures and topologies. The Multiple Perceptron, for example, is a neural network that has a great capacity for generalisation, that is, when used for pattern classification, it is able to correctly classify samples that have never been presented to it, using only its experience with previous classifications. However, the generalisation capacity of the perceptron is proportional to the quality of its…mehr

Produktbeschreibung
Artificial intelligence is becoming increasingly present in our society. To this end, several strategies have been created. Artificial Neural Networks was one of them and has several architectures and topologies. The Multiple Perceptron, for example, is a neural network that has a great capacity for generalisation, that is, when used for pattern classification, it is able to correctly classify samples that have never been presented to it, using only its experience with previous classifications. However, the generalisation capacity of the perceptron is proportional to the quality of its topology, i.e., good generalisation requires good topology. However, finding the ideal topology for a perceptron is not a simple task. This work analyses the metrics used to find the best topology for a given problem.
Autorenporträt
Young scientist from Juruaia, Minas Gerais. Graduated in Computer Science from the University Centre of the Guaxupé Educational Foundation (UNIFEG), where he produced two scientific papers. The first of these, the seed of this work, was developed in 2014 and its summary was published at the 2nd UNIFEG scientific congress in the same year.