Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-02-03T20:53:53Z No. of bitstreams: 1 AlanPauloOliveiraDaSilva_TESE.pdf: 1827762 bytes, checksum: f478a28631ce88521aefb0bb1971ecff (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-02-04T00:09:56Z (GMT) No. of bitstreams: 1 AlanPauloOliveiraDaSilva_TESE.pdf: 1827762 bytes, checksum: f478a28631ce88521aefb0bb1971ecff (MD5) / Made available in DSpace on 2016-02-04T00:09:56Z (GMT). No. of bitstreams: 1 AlanPauloOliveiraDaSilva_TESE.pdf: 1827762 bytes, checksum: f478a28631ce88521aefb0bb1971ecff (MD5) Previous issue date: 2015-01-30 / Este trabalho prop?e a utiliza??o do modelo comportamental do ciclo de histerese do capacitor ferroel?trico como uma nova alternativa ?s t?cnicas normalmente custosas no c?lculo de fun??es n?o-lineares em neur?nios artificiais implementados em plataforma de hardware reconfigur?vel, no caso, um dispositivo FPGA. Inicialmente a proposta foi validada por meio da implementa??o da l?gica booleana atrav?s dos modelos digitais de dois neur?nios artificiais: o Perceptron e uma varia??o do modelo Spiking Neuron Integrate and Fire, ambos utilizando o modelo tamb?m digital do ciclo de histerese do capacitor ferroel?trico como unidade b?sica n?o-linear no c?lculo das sa?das dos neur?nios. Finalmente, foi utilizado um modelo anal?gico do capacitor ferroel?trico com o objetivo de verificar a sua efic?cia e uma poss?vel redu??o no n?mero de elementos l?gicos necess?- rios no caso da implementa??o dos neur?nios em circuito integrado. As implementa??es foram realizadas por meio de modelos em Simulink e a sintetiza??o dos mesmos foi feita com o aux?lio do software DSP Builder, da Altera Corporation. / This work proposes the use of the behavioral model of the hysteresis loop of the ferroelectrics capacitor as a new alternative to the usually costly techniques in the computation of nonlinear functions in artificial neurons implemented on reconfigurable hardware platform, in this case, a FPGA device. Initially the proposal has been validated by the implementation of the boolean logic through the digital models of two artificial neurons: the Perceptron and a variation of the model Integrate and Fire Spiking Neuron, both using the model also digital of the hysteresis loop of the ferroelectric capacitor as it?s basic nonlinear unit for the calculations of the neurons outputs. Finally, it has been used the analog model of the ferroelectric capacitor with the goal of verifying it?s effectiveness and possibly the reduction of the number of necessary logic elements in the case of implementing the artificial neurons on integrated circuit. The implementations has been carried out by Simulink models and the synthesizing has been done through the DSP Builder software from Altera Corporation.