Extração de conhecimento a partir de redes reurais recorrentes / knowledge extraction from recurrent neural networks

AUTOR(ES)

Denise Regina Pechmann Simon

DATA DE PUBLICAÇÃO

2004

RESUMO

ln this work a method ofknowledge extraction from Recurrent Neural Network is proposed. Express formally the knowledge stored inside an Artificial Neural Network is a great challenge, because such knowledge has to be reformulated and presented by simple and understandable means. Three symbolic formats are presented for the representation of this knowledge: Fuzzy Finite Automata, Markov Chains and Deterministic Finite Automata. For the knowledge extraction used in this work, each space region of the neuron activity is associated to a meaning. The considered method uses clusterization of the neural space in order to obtain the automata states, using the K-means algorithm and the fuzzy clustering. The knowledge acquisition is made using Recurrent Neural Networks to learn the behavior of the two non linear dynamic systems and, from the trained nets, to extract the states and possible automata transitions. The dynamic systems are the lnverse Pendulum system and the Lorenz system. The presented extraction method was validated with the knowledge representation of the two studied dynamic systems, through the three symbolic formats.

ASSUNTO(S)

lógica difusa redes neurais recorrentes recurrent neural network ciencia da computacao fuzzy logic finite state machine máquina de estados finita

Documentos Relacionados

• Extração de conhecimento de redes neurais artificiais.
• Extraction of knowledge from Artificial Neural Networks using Symbolic Machine Learning Systems and Genetic Algorithm
• Redes neurais recorrentes aplicadas à assimilação de dados em dinâmica não-linear
• Redes neurais recorrentes aplicadas à assimilação de dados em dinâmica não-linear
• Redes neurais recorrentes aplicadas à assimilação de dados em dinâmica não-linear