Archive for the 'Tri Lambda' Category

Cursos Online
Sunday, December 8th, 2013

coursera.org edx.org veduca.com.br khanacademy.org

Criador de gif com fórmula científica
Tuesday, December 3rd, 2013

http://www.codecogs.com/latex/eqneditor.php

Princípio de Pareto
Wednesday, August 22nd, 2012

http://pt.wikipedia.org/wiki/Princ%C3%ADpio_de_Pareto http://noticias.uol.com.br/economia/carreiras/ultnot/infomoney/2007/05/25/ult4229u501.jhtm

formas normais
Friday, April 6th, 2012

1a = não pode ter campos multivadorados 2a = nada pode depender de parte da chave, somente da chave inteira. 3a = nada pode depender de algo que nao seja a chave (nao pode haver dependencia transitiva)

Pesos sinápticos
Saturday, March 3rd, 2012

Pesos sinápticos podem ser positivos ou negativos, assim como as sinapses em neurônios biológicos podem ser excitatórias ou inibitórios.   W kj = conexão do neurônio j para o neurônio k

Fault-tolerance or graceful degradation
Saturday, March 3rd, 2012

“Fault-tolerance or graceful degradation is the property that enables a system (often computer-based) to continue operating properly in the event of the failure of (or one or more faults within) some of its components. If its operating quality decreases at all, the decrease is proportional to the severity of the failure, as compared to a naïvely-designed system in which even a […]

Evidential response
Saturday, March 3rd, 2012

Decision with a measure of confidence (http://pt.wikipedia.org/wiki/Intervalo_de_confian%C3%A7a ou http://en.wikipedia.org/wiki/Confidence_interval)

Adaptivity
Saturday, March 3rd, 2012

“Information is stored in the weight matrix W of a neural network. Learning is the determination of the weights. Following the way learning is performed, we can distinguish two major categories of neural networks:  fixed networks in which the weights cannot be changed, ie dW/dt=0. In such networks, the weights are fixed a priori according to […]

Neural networks can learn with a teacher or without a teacher
Saturday, March 3rd, 2012

Neural networks can learn with a teacher or without a teacher

Nonlinearity
Saturday, March 3rd, 2012

“In mathematics, a nonlinear system is one that does not satisfy the superposition principle, or one whose output is not directly proportional to its input; a linear system fulfills these conditions. In other words, a nonlinear system is any problem where the variable(s) to be solved for cannot be written as a linear combination of […]